Aryan Mokhtari

197 papers A* 35A 15C 2Misc 15Journal 112Unranked 18

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Adaptive Matrix Online Learning through Smoothing with Guarantees for Nonsmooth Nonconvex Optimization. CoRR Ruichen Jiang, Zakaria Mhammedi, Mehryar Mohri, Aryan Mokhtari
2026	J	`jnl`	Adaptive Optimization via Momentum on Variance-Normalized Gradients. CoRR Francisco Patitucci, Aryan Mokhtari
2026	J	`jnl`	Aletheia tackles FirstProof autonomously. CoRR Tony Feng, Junehyuk Jung, Sang-hyun Kim, Carlo Pagano, Sergei Gukov, Cheng-Chiang Tsai, David P. Woodruff, Adel Javanmard, Aryan Mokhtari, Dawsen Hwang, Yuri Chervonyi, Jonathan N. Lee, Garrett Bingham, Trieu H. Trinh, Vahab Mirrokni, Quoc V. Le, Thang Luong
2026	J	`jnl`	CARE-RFT: Confidence-Anchored Reinforcement Finetuning for Reliable Reasoning in Large Language Models. CoRR Shuozhe Li, Jincheng Cao, Bodun Hu, Aryan Mokhtari, Leqi Liu, Amy Zhang
2026	J	`jnl`	Statistical Learning from Attribution Sets. CoRR Lorne Applebaum, Róbert Busa-Fekete, August Y. Chen, Claudio Gentile, Tomer Koren, Aryan Mokhtari
2026	J	`jnl`	Temper-Then-Tilt: Principled Unlearning for Generative Models through Tempering and Classifier Guidance. CoRR Jacob L. Block, Mehryar Mohri, Aryan Mokhtari, Sanjay Shakkottai
2025	J	`jnl`	Affine-Invariant Global Non-Asymptotic Convergence Analysis of BFGS under Self-Concordance. CoRR Qiujiang Jin, Aryan Mokhtari
2025	J	`jnl`	Generalized Optimistic Methods for Convex-Concave Saddle Point Problems. SIAM J. Optim. Ruichen Jiang, Aryan Mokhtari
2025	A*	`conf`	Improved Complexity for Smooth Nonconvex Optimization: A Two-Level Online Learning Approach with Quasi-Newton Methods. STOC Ruichen Jiang, Aryan Mokhtari, Francisco Patitucci
2025	J	`jnl`	Improving Online-to-Nonconvex Conversion for Smooth Optimization via Double Optimism. CoRR Francisco Patitucci, Ruichen Jiang, Aryan Mokhtari
2025	A*	`conf`	Learning Mixtures of Experts with EM: A Mirror Descent Perspective. ICML Quentin Fruytier, Aryan Mokhtari, Sujay Sanghavi
2025	J	`jnl`	Machine Unlearning under Overparameterization. CoRR Jacob L. Block, Aryan Mokhtari, Sanjay Shakkottai
2025	J	`jnl`	On the Complexity of Finding Stationary Points in Nonconvex Simple Bilevel Optimization. CoRR Jincheng Cao, Ruichen Jiang, Erfan Yazdandoost Hamedani, Aryan Mokhtari
2025	A*	`conf`	On the Crucial Role of Initialization for Matrix Factorization. ICLR Bingcong Li, Liang Zhang, Aryan Mokhtari, Niao He
2025	J	`jnl`	Online Learning-guided Learning Rate Adaptation via Gradient Alignment. CoRR Ruichen Jiang, Ali Kavis, Aryan Mokhtari
2025	A*	`conf`	Provable Complexity Improvement of AdaGrad over SGD: Upper and Lower Bounds in Stochastic Non-Convex Optimization. COLT Ruichen Jiang, Devyani Maladkar, Aryan Mokhtari
2025	J	`jnl`	Sculpting Latent Spaces With MMD: Disentanglement With Programmable Priors. CoRR Quentin Fruytier, Akshay Malhotra, Shahab Hamidi-Rad, Aditya Sant, Aryan Mokhtari, Sujay Sanghavi
2024	A*	`conf`	Adaptive and Optimal Second-order Optimistic Methods for Minimax Optimization. NeurIPS Ruichen Jiang, Ali Kavis, Qiujiang Jin, Sujay Sanghavi, Aryan Mokhtari
2024	J	`jnl`	Adaptive and Optimal Second-order Optimistic Methods for Minimax Optimization. CoRR Ruichen Jiang, Ali Kavis, Qiujiang Jin, Sujay Sanghavi, Aryan Mokhtari
2024	A*	`conf`	An Accelerated Gradient Method for Convex Smooth Simple Bilevel Optimization. NeurIPS Jincheng Cao, Ruichen Jiang, Erfan Yazdandoost Hamedani, Aryan Mokhtari
2024	J	`jnl`	An Accelerated Gradient Method for Simple Bilevel Optimization with Convex Lower-level Problem. CoRR Jincheng Cao, Ruichen Jiang, Erfan Yazdandoost Hamedani, Aryan Mokhtari
2024	J	`jnl`	Convergence Analysis of Adaptive Gradient Methods under Refined Smoothness and Noise Assumptions. CoRR Devyani Maladkar, Ruichen Jiang, Aryan Mokhtari
2024	J	`jnl`	Improved Complexity for Smooth Nonconvex Optimization: A Two-Level Online Learning Approach with Quasi-Newton Methods. CoRR Ruichen Jiang, Aryan Mokhtari, Francisco Patitucci
2024	A*	`conf`	In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness. NeurIPS Liam Collins, Advait Parulekar, Aryan Mokhtari, Sujay Sanghavi, Sanjay Shakkottai
2024	J	`jnl`	In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness. CoRR Liam Collins, Advait Parulekar, Aryan Mokhtari, Sujay Sanghavi, Sanjay Shakkottai
2024	A	`conf`	Krylov Cubic Regularized Newton: A Subspace Second-Order Method with Dimension-Free Convergence Rate. AISTATS Ruichen Jiang, Parameswaran Raman, Shoham Sabach, Aryan Mokhtari, Mingyi Hong, Volkan Cevher
2024	J	`jnl`	Krylov Cubic Regularized Newton: A Subspace Second-Order Method with Dimension-Free Convergence Rate. CoRR Ruichen Jiang, Parameswaran Raman, Shoham Sabach, Aryan Mokhtari, Mingyi Hong, Volkan Cevher
2024	J	`jnl`	Learning Mixtures of Experts with EM. CoRR Quentin Fruytier, Aryan Mokhtari, Sujay Sanghavi
2024	A*	`conf`	Non-asymptotic Global Convergence Analysis of BFGS with the Armijo-Wolfe Line Search. NeurIPS Qiujiang Jin, Ruichen Jiang, Aryan Mokhtari
2024	J	`jnl`	On the Crucial Role of Initialization for Matrix Factorization. CoRR Bingcong Li, Liang Zhang, Aryan Mokhtari, Niao He
2024	J	`jnl`	Online Learning Guided Quasi-Newton Methods with Global Non-Asymptotic Convergence. CoRR Ruichen Jiang, Aryan Mokhtari
2024	J	`jnl`	Provable Meta-Learning with Low-Rank Adaptations. CoRR Jacob L. Block, Sundararajan Srinivasan, Liam Collins, Aryan Mokhtari, Sanjay Shakkottai
2024	A*	`conf`	Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks. ICML Liam Collins, Hamed Hassani, Mahdi Soltanolkotabi, Aryan Mokhtari, Sanjay Shakkottai
2024	J	`jnl`	Statistical and Computational Complexities of BFGS Quasi-Newton Method for Generalized Linear Models. Trans. Mach. Learn. Res. Qiujiang Jin, Tongzheng Ren, Nhat Ho, Aryan Mokhtari
2024	A*	`conf`	Stochastic Newton Proximal Extragradient Method. NeurIPS Ruichen Jiang, Michal Derezinski, Aryan Mokhtari
2024	J	`jnl`	Stochastic Newton Proximal Extragradient Method. CoRR Ruichen Jiang, Michal Derezinski, Aryan Mokhtari
2023	A	`conf`	A Conditional Gradient-based Method for Simple Bilevel Optimization with Convex Lower-level Problem. AISTATS Ruichen Jiang, Nazanin Abolfazli, Aryan Mokhtari, Erfan Yazdandoost Hamedani
2023	A*	`conf`	Accelerated Quasi-Newton Proximal Extragradient: Faster Rate for Smooth Convex Optimization. NeurIPS Ruichen Jiang, Aryan Mokhtari
2023	J	`jnl`	Accelerated Quasi-Newton Proximal Extragradient: Faster Rate for Smooth Convex Optimization. CoRR Ruichen Jiang, Aryan Mokhtari
2023	J	`jnl`	Greedy Pruning with Group Lasso Provably Generalizes for Matrix Sensing and Neural Networks with Quadratic Activations. CoRR Nived Rajaraman, Devvrit, Aryan Mokhtari, Kannan Ramchandran
2023	A*	`conf`	Greedy Pruning with Group Lasso Provably Generalizes for Matrix Sensing. NeurIPS Nived Rajaraman, Devvrit, Aryan Mokhtari, Kannan Ramchandran
2023	A*	`conf`	InfoNCE Loss Provably Learns Cluster-Preserving Representations. COLT Advait Parulekar, Liam Collins, Karthikeyan Shanmugam, Aryan Mokhtari, Sanjay Shakkottai
2023	J	`jnl`	InfoNCE Loss Provably Learns Cluster-Preserving Representations. CoRR Advait Parulekar, Liam Collins, Karthikeyan Shanmugam, Aryan Mokhtari, Sanjay Shakkottai
2023	J	`jnl`	Limited-Memory Greedy Quasi-Newton Method with Non-asymptotic Superlinear Convergence Rate. CoRR Zhan Gao, Aryan Mokhtari, Alec Koppel
2023	Misc	`conf`	Meta-Learning for Image-Guided Millimeter-Wave Beam Selection in Unseen Environments. ICASSP Jerry Gu, Liam Collins, Debashri Roy, Aryan Mokhtari, Sanjay Shakkottai, Kaushik R. Chowdhury
2023	A*	`conf`	Network Adaptive Federated Learning: Congestion and Lossy Compression. INFOCOM Parikshit Hegde, Gustavo de Veciana, Aryan Mokhtari
2023	J	`jnl`	Network Adaptive Federated Learning: Congestion and Lossy Compression. CoRR Parikshit Hegde, Gustavo de Veciana, Aryan Mokhtari
2023	J	`jnl`	Non-asymptotic superlinear convergence of standard quasi-Newton methods. Math. Program. Qiujiang Jin, Aryan Mokhtari
2023	A*	`conf`	Online Learning Guided Curvature Approximation: A Quasi-Newton Method with Global Non-Asymptotic Superlinear Convergence. COLT Ruichen Jiang, Qiujiang Jin, Aryan Mokhtari
2023	J	`jnl`	Online Learning Guided Curvature Approximation: A Quasi-Newton Method with Global Non-Asymptotic Superlinear Convergence. CoRR Ruichen Jiang, Qiujiang Jin, Aryan Mokhtari
2023	A*	`conf`	Projection-Free Methods for Stochastic Simple Bilevel Optimization with Convex Lower-level Problem. NeurIPS Jincheng Cao, Ruichen Jiang, Nazanin Abolfazli, Erfan Yazdandoost Hamedani, Aryan Mokhtari
2023	J	`jnl`	Projection-Free Methods for Stochastic Simple Bilevel Optimization with Convex Lower-level Problem. CoRR Jincheng Cao, Ruichen Jiang, Nazanin Abolfazli, Erfan Yazdandoost Hamedani, Aryan Mokhtari
2023	J	`jnl`	Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks. CoRR Liam Collins, Hamed Hassani, Mahdi Soltanolkotabi, Aryan Mokhtari, Sanjay Shakkottai
2023	J	`jnl`	Provably Private Distributed Averaging Consensus: An Information-Theoretic Approach. IEEE Trans. Inf. Theory Mohammad Fereydounian, Aryan Mokhtari, Ramtin Pedarsani, Hamed Hassani
2023	J	`jnl`	Straggler-Resilient Personalized Federated Learning. Trans. Mach. Learn. Res. Isidoros Tziotis, Zebang Shen, Ramtin Pedarsani, Hamed Hassani, Aryan Mokhtari
2022	Misc	`conf`	Adaptive Node Participation for Straggler-Resilient Federated Learning. ICASSP Amirhossein Reisizadeh, Isidoros Tziotis, Hamed Hassani, Aryan Mokhtari, Ramtin Pedarsani
2022	A*	`conf`	FedAvg with Fine Tuning: Local Updates Lead to Representation Learning. NeurIPS Liam Collins, Hamed Hassani, Aryan Mokhtari, Sanjay Shakkottai
2022	J	`jnl`	FedAvg with Fine Tuning: Local Updates Lead to Representation Learning. CoRR Liam Collins, Hamed Hassani, Aryan Mokhtari, Sanjay Shakkottai
2022	J	`jnl`	Future Gradient Descent for Adapting the Temporal Shifting Data Distribution in Online Recommendation Systems. CoRR Mao Ye, Ruichen Jiang, Haoxiang Wang, Dhruv Choudhary, Xiaocong Du, Bhargav Bhushanam, Aryan Mokhtari, Arun Kejariwal, Qiang Liu
2022	A	`conf`	Future gradient descent for adapting the temporal shifting data distribution in online recommendation systems. UAI Mao Ye, Ruichen Jiang, Haoxiang Wang, Dhruv Choudhary, Xiaocong Du, Bhargav Bhushanam, Aryan Mokhtari, Arun Kejariwal, Qiang Liu
2022	J	`jnl`	Generalized Frank-Wolfe Algorithm for Bilevel Optimization. CoRR Ruichen Jiang, Nazanin Abolfazli, Aryan Mokhtari, Erfan Yazdandoost Hamedani
2022	J	`jnl`	Generalized Optimistic Methods for Convex-Concave Saddle Point Problems. CoRR Ruichen Jiang, Aryan Mokhtari
2022	—	`conf`	How Does the Task Landscape Affect MAML Performance? CoLLAs Liam Collins, Aryan Mokhtari, Sanjay Shakkottai
2022	—	`conf`	Leveraging Synergies Between AI and Networking to Build Next Generation Edge Networks. CIC Sen Lin, Ming Shi, Anish Arora, Raef Bassily, Elisa Bertino, Constantine Caramanis, Kaushik R. Chowdhury, Eylem Ekici, Atilla Eryilmaz, Stratis Ioannidis, Nan Jiang, Gauri Joshi, Jim Kurose, Yingbin Liang, Zhiqiang Lin, Jia Liu, Mingyan Liu, Tommaso Melodia, Aryan Mokhtari, Rob Nowak, Sewoong Oh, Srini Parthasarathy, Chunyi Peng, Hulya Seferoglu, Ness B. Shroff, Sanjay Shakkottai, Kannan Srinivasan, Ameet Talwalkar, Aylin Yener, Lei Ying
2022	A*	`conf`	MAML and ANIL Provably Learn Representations. ICML Liam Collins, Aryan Mokhtari, Sewoong Oh, Sanjay Shakkottai
2022	J	`jnl`	MAML and ANIL Provably Learn Representations. CoRR Liam Collins, Aryan Mokhtari, Sewoong Oh, Sanjay Shakkottai
2022	A	`conf`	Minimax Optimization: The Case of Convex-Submodular. AISTATS Arman Adibi, Aryan Mokhtari, Hamed Hassani
2022	J	`jnl`	Provably Private Distributed Averaging Consensus: An Information-Theoretic Approach. CoRR Mohammad Fereydounian, Aryan Mokhtari, Ramtin Pedarsani, Hamed Hassani
2022	A*	`conf`	Sharpened Quasi-Newton Methods: Faster Superlinear Rate and Larger Local Convergence Neighborhood. ICML Qiujiang Jin, Alec Koppel, Ketan Rajawat, Aryan Mokhtari
2022	J	`jnl`	Straggler-Resilient Federated Learning: Leveraging the Interplay Between Statistical Accuracy and System Heterogeneity. IEEE J. Sel. Areas Inf. Theory Amirhossein Reisizadeh, Isidoros Tziotis, Hamed Hassani, Aryan Mokhtari, Ramtin Pedarsani
2022	J	`jnl`	Straggler-Resilient Personalized Federated Learning. CoRR Isidoros Tziotis, Zebang Shen, Ramtin Pedarsani, Hamed Hassani, Aryan Mokhtari
2022	A*	`conf`	The Power of Adaptivity in SGD: Self-Tuning Step Sizes with Unbounded Gradients and Affine Variance. COLT Matthew Faw, Isidoros Tziotis, Constantine Caramanis, Aryan Mokhtari, Sanjay Shakkottai, Rachel A. Ward
2022	J	`jnl`	The Power of Adaptivity in SGD: Self-Tuning Step Sizes with Unbounded Gradients and Affine Variance. CoRR Matthew Faw, Isidoros Tziotis, Constantine Caramanis, Aryan Mokhtari, Sanjay Shakkottai, Rachel A. Ward
2021	A*	`conf`	Exploiting Local Convergence of Quasi-Newton Methods Globally: Adaptive Sample Size Approach. NeurIPS Qiujiang Jin, Aryan Mokhtari
2021	J	`jnl`	Exploiting Local Convergence of Quasi-Newton Methods Globally: Adaptive Sample Size Approach. CoRR Qiujiang Jin, Aryan Mokhtari
2021	A*	`conf`	Exploiting Shared Representations for Personalized Federated Learning. ICML Liam Collins, Hamed Hassani, Aryan Mokhtari, Sanjay Shakkottai
2021	J	`jnl`	Exploiting Shared Representations for Personalized Federated Learning. CoRR Liam Collins, Hamed Hassani, Aryan Mokhtari, Sanjay Shakkottai
2021	A	`conf`	Federated Learning with Compression: Unified Analysis and Sharp Guarantees. AISTATS Farzin Haddadpour, Mohammad Mahdi Kamani, Aryan Mokhtari, Mehrdad Mahdavi
2021	A*	`conf`	Generalization of Model-Agnostic Meta-Learning Algorithms: Recurring and Unseen Tasks. NeurIPS Alireza Fallah, Aryan Mokhtari, Asuman E. Ozdaglar
2021	J	`jnl`	Generalization of Model-Agnostic Meta-Learning Algorithms: Recurring and Unseen Tasks. CoRR Alireza Fallah, Aryan Mokhtari, Asuman E. Ozdaglar
2021	J	`jnl`	Minimax Optimization: The Case of Convex-Submodular. CoRR Arman Adibi, Aryan Mokhtari, Hamed Hassani
2021	A*	`conf`	On the Convergence Theory of Debiased Model-Agnostic Meta-Reinforcement Learning. NeurIPS Alireza Fallah, Kristian Georgiev, Aryan Mokhtari, Asuman E. Ozdaglar
2020	J	`jnl`	A Class of Parallel Doubly Stochastic Algorithms for Large-Scale Learning. J. Mach. Learn. Res. Aryan Mokhtari, Alec Koppel, Martin Takác, Alejandro Ribeiro
2020	A	`conf`	A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach. AISTATS Aryan Mokhtari, Asuman E. Ozdaglar, Sarath Pattathil
2020	J	`jnl`	Convergence Rate of 풪(1/k) for Optimistic Gradient and Extragradient Methods in Smooth Convex-Concave Saddle Point Problems. SIAM J. Optim. Aryan Mokhtari, Asuman E. Ozdaglar, Sarath Pattathil
2020	A	`conf`	DAve-QN: A Distributed Averaged Quasi-Newton Method with Local Superlinear Convergence Rate. AISTATS Saeed Soori, Konstantin Mishchenko, Aryan Mokhtari, Maryam Mehri Dehnavi, Mert Gürbüzbalaban
2020	J	`jnl`	Distribution-Agnostic Model-Agnostic Meta-Learning. CoRR Liam Collins, Aryan Mokhtari, Sanjay Shakkottai
2020	A	`conf`	Efficient Distributed Hessian Free Algorithm for Large-scale Empirical Risk Minimization via Accumulating Sample Strategy. AISTATS Majid Jahani, Xi He, Chenxin Ma, Aryan Mokhtari, Dheevatsa Mudigere, Alejandro Ribeiro, Martin Takác
2020	A	`conf`	FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization. AISTATS Amirhossein Reisizadeh, Aryan Mokhtari, Hamed Hassani, Ali Jadbabaie, Ramtin Pedarsani
2020	J	`jnl`	Federated Learning with Compression: Unified Analysis and Sharp Guarantees. CoRR Farzin Haddadpour, Mohammad Mahdi Kamani, Aryan Mokhtari, Mehrdad Mahdavi
2020	J	`jnl`	High-Dimensional Nonconvex Stochastic Optimization by Doubly Stochastic Successive Convex Approximation. IEEE Trans. Signal Process. Aryan Mokhtari, Alec Koppel
2020	J	`jnl`	Non-asymptotic Superlinear Convergence of Standard Quasi-Newton Methods. CoRR Qiujiang Jin, Aryan Mokhtari
2020	A	`conf`	On the Convergence Theory of Gradient-Based Model-Agnostic Meta-Learning Algorithms. AISTATS Alireza Fallah, Aryan Mokhtari, Asuman E. Ozdaglar
2020	A	`conf`	One Sample Stochastic Frank-Wolfe. AISTATS Mingrui Zhang, Zebang Shen, Aryan Mokhtari, Hamed Hassani, Amin Karbasi
2020	A*	`conf`	Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach. NeurIPS Alireza Fallah, Aryan Mokhtari, Asuman E. Ozdaglar
2020	J	`jnl`	Personalized Federated Learning: A Meta-Learning Approach. CoRR Alireza Fallah, Aryan Mokhtari, Asuman E. Ozdaglar
2020	J	`jnl`	Provably Convergent Policy Gradient Methods for Model-Agnostic Meta-Reinforcement Learning. CoRR Alireza Fallah, Aryan Mokhtari, Asuman E. Ozdaglar
2020	A*	`conf`	Quantized Decentralized Stochastic Learning over Directed Graphs. ICML Hossein Taheri, Aryan Mokhtari, Hamed Hassani, Ramtin Pedarsani
2020	A	`conf`	Quantized Frank-Wolfe: Faster Optimization, Lower Communication, and Projection Free. AISTATS Mingrui Zhang, Lin Chen, Aryan Mokhtari, Hamed Hassani, Amin Karbasi
2020	J	`jnl`	Quantized Push-sum for Gossip and Decentralized Optimization over Directed Graphs. CoRR Hossein Taheri, Aryan Mokhtari, Hamed Hassani, Ramtin Pedarsani
2020	J	`jnl`	Safe Learning under Uncertain Objectives and Constraints. CoRR Mohammad Fereydounian, Zebang Shen, Aryan Mokhtari, Amin Karbasi, Hamed Hassani
2020	A*	`conf`	Second Order Optimality in Decentralized Non-Convex Optimization via Perturbed Gradient Tracking. NeurIPS Isidoros Tziotis, Constantine Caramanis, Aryan Mokhtari
2020	J	`jnl`	Stochastic Conditional Gradient Methods: From Convex Minimization to Submodular Maximization. J. Mach. Learn. Res. Aryan Mokhtari, Hamed Hassani, Amin Karbasi
2020	J	`jnl`	Stochastic Conditional Gradient++: (Non)Convex Minimization and Continuous Submodular Maximization. SIAM J. Optim. Hamed Hassani, Amin Karbasi, Aryan Mokhtari, Zebang Shen
2020	J	`jnl`	Stochastic Quasi-Newton Methods. Proc. IEEE Aryan Mokhtari, Alejandro Ribeiro
2020	J	`jnl`	Straggler-Resilient Federated Learning: Leveraging the Interplay Between Statistical Accuracy and System Heterogeneity. CoRR Amirhossein Reisizadeh, Isidoros Tziotis, Hamed Hassani, Aryan Mokhtari, Ramtin Pedarsani
2020	A*	`conf`	Submodular Meta-Learning. NeurIPS Arman Adibi, Aryan Mokhtari, Hamed Hassani
2020	J	`jnl`	Submodular Meta-Learning. CoRR Arman Adibi, Aryan Mokhtari, Hamed Hassani
2020	A*	`conf`	Task-Robust Model-Agnostic Meta-Learning. NeurIPS Liam Collins, Aryan Mokhtari, Sanjay Shakkottai
2020	J	`jnl`	Why Does MAML Outperform ERM? An Optimization Perspective. CoRR Liam Collins, Aryan Mokhtari, Sanjay Shakkottai
2019	J	`jnl`	A Decentralized Proximal Point-type Method for Saddle Point Problems. CoRR Weijie Liu, Aryan Mokhtari, Asuman E. Ozdaglar, Sarath Pattathil, Zebang Shen, Nenggan Zheng
2019	J	`jnl`	A Newton-Based Method for Nonconvex Optimization with Fast Evasion of Saddle Points. SIAM J. Optim. Santiago Paternain, Aryan Mokhtari, Alejandro Ribeiro
2019	J	`jnl`	A Primal-Dual Quasi-Newton Method for Exact Consensus Optimization. IEEE Trans. Signal Process. Mark Eisen, Aryan Mokhtari, Alejandro Ribeiro
2019	J	`jnl`	A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach. CoRR Aryan Mokhtari, Asuman E. Ozdaglar, Sarath Pattathil
2019	C	`conf`	Achieving Acceleration in Distributed Optimization via Direct Discretization of the Heavy-Ball ODE. ACC Jingzhao Zhang, César A. Uribe, Aryan Mokhtari, Ali Jadbabaie
2019	J	`jnl`	An Exact Quantized Decentralized Gradient Descent Algorithm. IEEE Trans. Signal Process. Amirhossein Reisizadeh, Aryan Mokhtari, Hamed Hassani, Ramtin Pedarsani
2019	A	`conf`	Efficient Nonconvex Empirical Risk Minimization via Adaptive Sample Size Methods. AISTATS Aryan Mokhtari, Asuman E. Ozdaglar, Ali Jadbabaie
2019	J	`jnl`	FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization. CoRR Amirhossein Reisizadeh, Aryan Mokhtari, Hamed Hassani, Ali Jadbabaie, Ramtin Pedarsani
2019	J	`jnl`	On the Convergence Theory of Gradient-Based Model-Agnostic Meta-Learning Algorithms. CoRR Alireza Fallah, Aryan Mokhtari, Asuman E. Ozdaglar
2019	J	`jnl`	One Sample Stochastic Frank-Wolfe. CoRR Mingrui Zhang, Zebang Shen, Aryan Mokhtari, Hamed Hassani, Amin Karbasi
2019	J	`jnl`	Proximal Point Approximations Achieving a Convergence Rate of O(1/k) for Smooth Convex-Concave Saddle Point Problems: Optimistic Gradient and Extra-gradient Methods. CoRR Aryan Mokhtari, Asuman E. Ozdaglar, Sarath Pattathil
2019	J	`jnl`	Quantized Frank-Wolfe: Communication-Efficient Distributed Optimization. CoRR Mingrui Zhang, Lin Chen, Aryan Mokhtari, Hamed Hassani, Amin Karbasi
2019	A*	`conf`	Robust and Communication-Efficient Collaborative Learning. NeurIPS Amirhossein Reisizadeh, Hossein Taheri, Aryan Mokhtari, Hamed Hassani, Ramtin Pedarsani
2019	J	`jnl`	Robust and Communication-Efficient Collaborative Learning. CoRR Amirhossein Reisizadeh, Hossein Taheri, Aryan Mokhtari, Hamed Hassani, Ramtin Pedarsani
2019	J	`jnl`	Stochastic Conditional Gradient++. CoRR Hamed Hassani, Amin Karbasi, Aryan Mokhtari, Zebang Shen
2019	A*	`conf`	Stochastic Continuous Greedy ++: When Upper and Lower Bounds Match. NeurIPS Amin Karbasi, Hamed Hassani, Aryan Mokhtari, Zebang Shen
2018	—	`conf`	A Newton Method for Faster Navigation in Cluttered Environments. CDC Santiago Paternain, Aryan Mokhtari, Alejandro Ribeiro
2018	A	`conf`	Conditional Gradient Method for Stochastic Submodular Maximization: Closing the Gap. AISTATS Aryan Mokhtari, Hamed Hassani, Amin Karbasi
2018	A*	`conf`	Decentralized Submodular Maximization: Bridging Discrete and Continuous Settings. ICML Aryan Mokhtari, Hamed Hassani, Amin Karbasi
2018	A*	`conf`	Direct Runge-Kutta Discretization Achieves Acceleration. NeurIPS Jingzhao Zhang, Aryan Mokhtari, Suvrit Sra, Ali Jadbabaie
2018	J	`jnl`	Direct Runge-Kutta Discretization Achieves Acceleration. CoRR Jingzhao Zhang, Aryan Mokhtari, Suvrit Sra, Ali Jadbabaie
2018	J	`jnl`	Efficient Distributed Hessian Free Algorithm for Large-scale Empirical Risk Minimization via Accumulating Sample Strategy. CoRR Majid Jahani, Xi He, Chenxin Ma, Aryan Mokhtari, Dheevatsa Mudigere, Alejandro Ribeiro, Martin Takác
2018	A*	`conf`	Escaping Saddle Points in Constrained Optimization. NeurIPS Aryan Mokhtari, Asuman E. Ozdaglar, Ali Jadbabaie
2018	J	`jnl`	Escaping Saddle Points in Constrained Optimization. CoRR Aryan Mokhtari, Asuman E. Ozdaglar, Ali Jadbabaie
2018	J	`jnl`	IQN: An Incremental Quasi-Newton Method with Local Superlinear Convergence Rate. SIAM J. Optim. Aryan Mokhtari, Mark Eisen, Alejandro Ribeiro
2018	A	`conf`	Large Scale Empirical Risk Minimization via Truncated Adaptive Newton Method. AISTATS Mark Eisen, Aryan Mokhtari, Alejandro Ribeiro
2018	Misc	`conf`	Parallel Stochastic Successive Convex Approximation Method for Large-Scale Dictionary Learning. ICASSP Alec Koppel, Aryan Mokhtari, Alejandro Ribeiro
2018	—	`conf`	Quantized Decentralized Consensus Optimization. CDC Amirhossein Reisizadeh, Aryan Mokhtari, Hamed Hassani, Ramtin Pedarsani
2018	J	`jnl`	Quantized Decentralized Consensus Optimization. CoRR Amirhossein Reisizadeh, Aryan Mokhtari, S. Hamed Hassani, Ramtin Pedarsani
2018	J	`jnl`	Stochastic Conditional Gradient Methods: From Convex Minimization to Submodular Maximization. CoRR Aryan Mokhtari, Hamed Hassani, Amin Karbasi
2018	J	`jnl`	Surpassing Gradient Descent Provably: A Cyclic Incremental Method with Linear Convergence Rate. SIAM J. Optim. Aryan Mokhtari, Mert Gürbüzbalaban, Alejandro Ribeiro
2018	A*	`conf`	Towards More Efficient Stochastic Decentralized Learning: Faster Convergence and Sparse Communication. ICML Zebang Shen, Aryan Mokhtari, Tengfei Zhou, Peilin Zhao, Hui Qian
2018	J	`jnl`	Towards More Efficient Stochastic Decentralized Learning: Faster Convergence and Sparse Communication. CoRR Zebang Shen, Aryan Mokhtari, Tengfei Zhou, Peilin Zhao, Hui Qian
2017	Misc	`conf`	A Diagonal-Augmented quasi-Newton method with application to factorization machines. ICASSP Aryan Mokhtari, Amir Ingber
2017	Misc	`conf`	A double incremental aggregated gradient method with linear convergence rate for large-scale optimization. ICASSP Aryan Mokhtari, Mert Gürbüzbalaban, Alejandro Ribeiro
2017	Misc	`conf`	A primal-dual Quasi-Newton method for consensus optimization. ACSSC Mark Eisen, Aryan Mokhtari, Alejandro Ribeiro
2017	Misc	`conf`	An incremental quasi-Newton method with a local superlinear convergence rate. ICASSP Aryan Mokhtari, Mark Eisen, Alejandro Ribeiro
2017	J	`jnl`	Conditional Gradient Method for Stochastic Submodular Maximization: Closing the Gap. CoRR Aryan Mokhtari, S. Hamed Hassani, Amin Karbasi
2017	J	`jnl`	Decentralized Prediction-Correction Methods for Networked Time-Varying Convex Optimization. IEEE Trans. Autom. Control. Andrea Simonetto, Alec Koppel, Aryan Mokhtari, Geert Leus, Alejandro Ribeiro
2017	J	`jnl`	Decentralized Quasi-Newton Methods. IEEE Trans. Signal Process. Mark Eisen, Aryan Mokhtari, Alejandro Ribeiro
2017	—	`conf`	First-Order Adaptive Sample Size Methods to Reduce Complexity of Empirical Risk Minimization. NIPS Aryan Mokhtari, Alejandro Ribeiro
2017	J	`jnl`	First-Order Adaptive Sample Size Methods to Reduce Complexity of Empirical Risk Minimization. CoRR Aryan Mokhtari, Alejandro Ribeiro
2017	J	`jnl`	IQN: An Incremental Quasi-Newton Method with Local Superlinear Convergence Rate. CoRR Aryan Mokhtari, Mark Eisen, Alejandro Ribeiro
2017	J	`jnl`	Large Scale Empirical Risk Minimization via Truncated Adaptive Newton Method. CoRR Mark Eisen, Aryan Mokhtari, Alejandro Ribeiro
2017	Misc	`conf`	Large-scale nonconvex stochastic optimization by Doubly Stochastic Successive Convex approximation. ICASSP Aryan Mokhtari, Alec Koppel, Gesualdo Scutari, Alejandro Ribeiro
2017	J	`jnl`	Network Newton Distributed Optimization Methods. IEEE Trans. Signal Process. Aryan Mokhtari, Qing Ling, Alejandro Ribeiro
2017	J	`jnl`	Stochastic Averaging for Constrained Optimization With Application to Online Resource Allocation. IEEE Trans. Signal Process. Tianyi Chen, Aryan Mokhtari, Xin Wang, Alejandro Ribeiro, Georgios B. Giannakis
2016	J	`jnl`	A Class of Parallel Doubly Stochastic Algorithms for Large-Scale Learning. CoRR Aryan Mokhtari, Alec Koppel, Alejandro Ribeiro
2016	J	`jnl`	A Class of Prediction-Correction Methods for Time-Varying Convex Optimization. IEEE Trans. Signal Process. Andrea Simonetto, Aryan Mokhtari, Alec Koppel, Geert Leus, Alejandro Ribeiro
2016	J	`jnl`	A Decentralized Quasi-Newton Method for Dual Formulations of Consensus Optimization. CoRR Mark Eisen, Aryan Mokhtari, Alejandro Ribeiro
2016	J	`jnl`	A Decentralized Second-Order Method with Exact Linear Convergence Rate for Consensus Optimization. CoRR Aryan Mokhtari, Wei Shi, Qing Ling, Alejandro Ribeiro
2016	J	`jnl`	A Decentralized Second-Order Method with Exact Linear Convergence Rate for Consensus Optimization. IEEE Trans. Signal Inf. Process. over Networks Aryan Mokhtari, Wei Shi, Qing Ling, Alejandro Ribeiro
2016	—	`conf`	A Quasi-newton prediction-correction method for decentralized dynamic convex optimization. ECC Andrea Simonetto, Alec Koppel, Aryan Mokhtari, Geert Leus, Alejandro Ribeiro
2016	—	`conf`	A data-driven approach to stochastic network optimization. GlobalSIP Tianyi Chen, Aryan Mokhtari, Xin Wang, Alejandro Ribeiro, Georgios B. Giannakis
2016	—	`conf`	A decentralized Second-Order Method for Dynamic Optimization. CDC Aryan Mokhtari, Wei Shi, Qing Ling, Alejandro Ribeiro
2016	—	`conf`	A decentralized quasi-Newton method for dual formulations of consensus optimization. CDC Mark Eisen, Aryan Mokhtari, Alejandro Ribeiro
2016	—	`conf`	Adaptive Newton Method for Empirical Risk Minimization to Statistical Accuracy. NIPS Aryan Mokhtari, Hadi Daneshmand, Aurélien Lucchi, Thomas Hofmann, Alejandro Ribeiro
2016	J	`jnl`	Adaptive Newton Method for Empirical Risk Minimization to Statistical Accuracy. CoRR Aryan Mokhtari, Alejandro Ribeiro
2016	—	`conf`	An asynchronous Quasi-Newton method for consensus optimization. GlobalSIP Mark Eisen, Aryan Mokhtari, Alejandro Ribeiro
2016	J	`jnl`	DQM: Decentralized Quadratically Approximated Alternating Direction Method of Multipliers. IEEE Trans. Signal Process. Aryan Mokhtari, Wei Shi, Qing Ling, Alejandro Ribeiro
2016	J	`jnl`	DSA: Decentralized Double Stochastic Averaging Gradient Algorithm. J. Mach. Learn. Res. Aryan Mokhtari, Alejandro Ribeiro
2016	J	`jnl`	Decentralized Prediction-Correction Methods for Networked Time-Varying Convex Optimization. CoRR Andrea Simonetto, Alec Koppel, Aryan Mokhtari, Geert Leus, Alejandro Ribeiro
2016	—	`conf`	Decentralized constrained consensus optimization with primal dual splitting projection. GlobalSIP Han Zhang, Wei Shi, Aryan Mokhtari, Alejandro Ribeiro, Qing Ling
2016	J	`jnl`	Doubly Random Parallel Stochastic Methods for Large Scale Learning. CoRR Aryan Mokhtari, Alec Koppel, Alejandro Ribeiro
2016	C	`conf`	Doubly random parallel stochastic methods for large scale learning. ACC Aryan Mokhtari, Alec Koppel, Alejandro Ribeiro
2016	Misc	`conf`	Doubly stochastic algorithms for large-scale optimization. ACSSC Alec Koppel, Aryan Mokhtari, Alejandro Ribeiro
2016	Misc	`conf`	ESOM: Exact second-order method for consensus optimization. ACSSC Aryan Mokhtari, Wei Shi, Qing Ling
2016	J	`jnl`	Online Optimization in Dynamic Environments: Improved Regret Rates for Strongly Convex Problems. CoRR Aryan Mokhtari, Shahin Shahrampour, Ali Jadbabaie, Alejandro Ribeiro
2016	—	`conf`	Online optimization in dynamic environments: Improved regret rates for strongly convex problems. CDC Aryan Mokhtari, Shahin Shahrampour, Ali Jadbabaie, Alejandro Ribeiro
2016	J	`jnl`	Stochastic Averaging for Constrained Optimization with Application to Online Resource Allocation. CoRR Tianyi Chen, Aryan Mokhtari, Xin Wang, Alejandro Ribeiro, Georgios B. Giannakis
2016	J	`jnl`	Surpassing Gradient Descent Provably: A Cyclic Incremental Method with Linear Convergence Rate. CoRR Aryan Mokhtari, Mert Gürbüzbalaban, Alejandro Ribeiro
2015	J	`jnl`	A Class of Prediction-Correction Methods for Time-Varying Convex Optimization. CoRR Andrea Simonetto, Aryan Mokhtari, Alec Koppel, Geert Leus, Alejandro Ribeiro
2015	—	`conf`	A decentralized prediction-correction method for networked time-varying convex optimization. CAMSAP Andrea Simonetto, Aryan Mokhtari, Alec Koppel, Geert Leus, Alejandro Ribeiro
2015	Misc	`conf`	An approximate Newton method for distributed optimization. ICASSP Aryan Mokhtari, Qing Ling, Alejandro Ribeiro
2015	Misc	`conf`	Decentralized double stochastic averaging gradient. ACSSC Aryan Mokhtari, Alejandro Ribeiro
2015	—	`conf`	Decentralized quadratically approximated alternating direction method of multipliers. GlobalSIP Aryan Mokhtari, Wei Shi, Qing Ling, Alejandro Ribeiro
2015	J	`jnl`	Global convergence of online limited memory BFGS. J. Mach. Learn. Res. Aryan Mokhtari, Alejandro Ribeiro
2015	Misc	`conf`	Prediction-correction methods for time-varying convex optimization. ACSSC Andrea Simonetto, Alec Koppel, Aryan Mokhtari, Geert Leus, Alejandro Ribeiro
2015	—	`conf`	Target tracking with dynamic convex optimization. GlobalSIP Alec Koppel, Andrea Simonetto, Aryan Mokhtari, Geert Leus, Alejandro Ribeiro
2014	J	`jnl`	A Quasi-Newton Method for Large Scale Support Vector Machines. CoRR Aryan Mokhtari, Alejandro Ribeiro
2014	Misc	`conf`	A quasi-Newton method for large scale support vector machines. ICASSP Aryan Mokhtari, Alejandro Ribeiro
2014	J	`jnl`	Global Convergence of Online Limited Memory BFGS. CoRR Aryan Mokhtari, Alejandro Ribeiro
2014	Misc	`conf`	Network Newton. ACSSC Aryan Mokhtari, Qing Ling, Alejandro Ribeiro
2014	J	`jnl`	RES: Regularized Stochastic BFGS Algorithm. CoRR Aryan Mokhtari, Alejandro Ribeiro
2014	J	`jnl`	RES: Regularized Stochastic BFGS Algorithm. IEEE Trans. Signal Process. Aryan Mokhtari, Alejandro Ribeiro
2013	—	`conf`	A dual stochastic DFP algorithm for optimal resource allocation in wireless systems. SPAWC Aryan Mokhtari, Alejandro Ribeiro
2013	—	`conf`	Regularized stochastic BFGS algorithm. GlobalSIP Aryan Mokhtari, Alejandro Ribeiro