Mikhail Khodak

57 papers A* 19B 1Journal 33Unranked 4

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Attention Retrieves, MLP Memorizes: Disentangling Trainable Components in the Transformer. CoRR Yihe Dong, Lorenzo Noci, Mikhail Khodak, Mufan Bill Li
2025	J	`jnl`	L2G: Repurposing Language Models for Genomics Tasks. Trans. Mach. Learn. Res. Wenduo Cheng, Junhong Shen, Mikhail Khodak, Jian Ma, Ameet Talwalkar
2025	J	`jnl`	PCGBandit: One-shot acceleration of transient PDE solvers via online-learned preconditioners. CoRR Mikhail Khodak, Min Ki Jung, Brian Wynne, Edmond Chow, Egemen Kolemen
2025	J	`jnl`	Pre-Generating Multi-Difficulty PDE Data for Few-Shot Neural PDE Solvers. CoRR Naman Choudhary, Vedant Singh, Ameet Talwalkar, Nicholas Matthew Boffi, Mikhail Khodak, Tanya Marwah
2025	A*	`conf`	Specialized Foundation Models Struggle to Beat Supervised Baselines. ICLR Zongzhe Xu, Ritvik Gupta, Wenduo Cheng, Alexander Shen, Junhong Shen, Ameet Talwalkar, Mikhail Khodak
2024	A*	`conf`	Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instances. ICLR Mikhail Khodak, Edmond Chow, Maria-Florina Balcan, Ameet Talwalkar
2024	J	`jnl`	Specialized Foundation Models Struggle to Beat Supervised Baselines. CoRR Zongzhe Xu, Ritvik Gupta, Wenduo Cheng, Alexander Shen, Junhong Shen, Ameet Talwalkar, Mikhail Khodak
2024	J	`jnl`	SureMap: Simultaneous Mean Estimation for Single-Task and Multi-Task Disaggregated Evaluation. CoRR Mikhail Khodak, Lester Mackey, Alexandra Chouldechova, Miroslav Dudík
2023	A*	`conf`	AANG : Automating Auxiliary Learning. ICLR Lucio M. Dery, Paul Michel, Mikhail Khodak, Graham Neubig, Ameet Talwalkar
2023	A*	`conf`	Cross-Modal Fine-Tuning: Align then Refine. ICML Junhong Shen, Liam Li, Lucio M. Dery, Corey Staten, Mikhail Khodak, Graham Neubig, Ameet Talwalkar
2023	J	`jnl`	Cross-Modal Fine-Tuning: Align then Refine. CoRR Junhong Shen, Liam Li, Lucio M. Dery, Corey Staten, Mikhail Khodak, Graham Neubig, Ameet Talwalkar
2023	J	`jnl`	Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instances. CoRR Mikhail Khodak, Edmond Chow, Maria-Florina Balcan, Ameet Talwalkar
2023	A*	`conf`	Learning-augmented private algorithms for multiple quantile release. ICML Mikhail Khodak, Kareem Amin, Travis Dick, Sergei Vassilvitskii
2023	J	`jnl`	Meta-Learning Adversarial Bandit Algorithms. CoRR Mikhail Khodak, Ilya Osadchiy, Keegan Harris, Maria-Florina Balcan, Kfir Y. Levy, Ron Meir, Zhiwei Steven Wu
2023	A*	`conf`	Meta-Learning in Games. ICLR Keegan Harris, Ioannis Anagnostides, Gabriele Farina, Mikhail Khodak, Steven Wu, Tuomas Sandholm
2023	—	`conf`	On Noisy Evaluation in Federated Hyperparameter Tuning. MLSys Kevin Kuo, Pratiksha Thaker, Mikhail Khodak, John Nguyen, Daniel Jiang, Ameet Talwalkar, Virginia Smith
2022	J	`jnl`	AANG: Automating Auxiliary Learning. CoRR Lucio M. Dery, Paul Michel, Mikhail Khodak, Graham Neubig, Ameet Talwalkar
2022	A*	`conf`	Efficient Architecture Search for Diverse Tasks. NeurIPS Junhong Shen, Mikhail Khodak, Ameet Talwalkar
2022	J	`jnl`	Efficient Architecture Search for Diverse Tasks. CoRR Junhong Shen, Mikhail Khodak, Ameet Talwalkar
2022	J	`jnl`	Learning Predictions for Algorithms with Predictions. CoRR Mikhail Khodak, Maria-Florina Balcan, Ameet Talwalkar, Sergei Vassilvitskii
2022	J	`jnl`	Meta-Learning Adversarial Bandits. CoRR Maria-Florina Balcan, Keegan Harris, Mikhail Khodak, Zhiwei Steven Wu
2022	J	`jnl`	Meta-Learning in Games. CoRR Keegan Harris, Ioannis Anagnostides, Gabriele Farina, Mikhail Khodak, Zhiwei Steven Wu, Tuomas Sandholm
2022	A*	`conf`	NAS-Bench-360: Benchmarking Neural Architecture Search on Diverse Tasks. NeurIPS Renbo Tu, Nicholas Roberts, Mikhail Khodak, Junhong Shen, Frederic Sala, Ameet Talwalkar
2022	J	`jnl`	On Noisy Evaluation in Federated Hyperparameter Tuning. CoRR Kevin Kuo, Pratiksha Thaker, Mikhail Khodak, John Nguyen, Daniel Jiang, Ameet Talwalkar, Virginia Smith
2022	J	`jnl`	Private Algorithms with Private Predictions. CoRR Kareem Amin, Travis Dick, Mikhail Khodak, Sergei Vassilvitskii
2022	J	`jnl`	Provably tuning the ElasticNet across instances. CoRR Maria-Florina Balcan, Mikhail Khodak, Dravyansh Sharma, Ameet Talwalkar
2021	J	`jnl`	Advances and Open Problems in Federated Learning. Found. Trends Mach. Learn. Peter Kairouz, H. Brendan McMahan, Brendan Avent, Aurélien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Kallista A. Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, Rafael G. L. D'Oliveira, Hubert Eichner, Salim El Rouayheb, David Evans, Josh Gardner, Zachary Garrett, Adrià Gascón, Badih Ghazi, Phillip B. Gibbons, Marco Gruteser, Zaïd Harchaoui, Chaoyang He, Lie He, Zhouyuan Huo, Ben Hutchinson, Justin Hsu, Martin Jaggi, Tara Javidi, Gauri Joshi, Mikhail Khodak, Jakub Konecný, Aleksandra Korolova, Farinaz Koushanfar, Sanmi Koyejo, Tancrède Lepoint, Yang Liu, Prateek Mittal, Mehryar Mohri, Richard Nock, Ayfer Özgür, Rasmus Pagh, Hang Qi, Daniel Ramage, Ramesh Raskar, Mariana Raykova, Dawn Song, Weikang Song, Sebastian U. Stich, Ziteng Sun, Ananda Theertha Suresh, Florian Tramèr, Praneeth Vepakomma, Jianyu Wang, Li Xiong, Zheng Xu, Qiang Yang, Felix X. Yu, Han Yu, Sen Zhao
2021	—	`conf`	AutoML Decathlon: Diverse Tasks, Modern Methods, and Efficiency at Scale. NeurIPS (Competition and Demos) Nicholas Roberts, Samuel Guo, Cong Xu, Ameet Talwalkar, David Lander, Lvfang Tao, Linhang Cai, Shuaicheng Niu, Jianyu Heng, Hongyang Qin, Minwen Deng, Johannes Hog, Alexander Pfefferle, Sushil Ammanaghatta Shivakumar, Arjun Krishnakumar, Yubo Wang, Rhea Sanjay Sukthanker, Frank Hutter, Euxhen Hasanaj, Tien-Dung Le, Mikhail Khodak, Yuriy Nevmyvaka, Kashif Rasul, Frederic Sala, Anderson Schneider, Junhong Shen, Evan Randall Sparks
2021	A*	`conf`	Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing. NeurIPS Mikhail Khodak, Renbo Tu, Tian Li, Liam Li, Maria-Florina Balcan, Virginia Smith, Ameet Talwalkar
2021	J	`jnl`	Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing. CoRR Mikhail Khodak, Renbo Tu, Tian Li, Liam Li, Maria-Florina Balcan, Virginia Smith, Ameet Talwalkar
2021	A*	`conf`	Geometry-Aware Gradient Algorithms for Neural Architecture Search. ICLR Liam Li, Mikhail Khodak, Nina Balcan, Ameet Talwalkar
2021	A*	`conf`	Initialization and Regularization of Factorized Neural Layers. ICLR Mikhail Khodak, Neil A. Tenenholtz, Lester Mackey, Nicolò Fusi
2021	J	`jnl`	Initialization and Regularization of Factorized Neural Layers. CoRR Mikhail Khodak, Neil A. Tenenholtz, Lester Mackey, Nicolò Fusi
2021	A*	`conf`	Learning-to-learn non-convex piecewise-Lipschitz functions. NeurIPS Maria-Florina Balcan, Mikhail Khodak, Dravyansh Sharma, Ameet Talwalkar
2021	J	`jnl`	Learning-to-learn non-convex piecewise-Lipschitz functions. CoRR Maria-Florina Balcan, Mikhail Khodak, Dravyansh Sharma, Ameet Talwalkar
2021	J	`jnl`	NAS-Bench-360: Benchmarking Diverse Tasks for Neural Architecture Search. CoRR Renbo Tu, Mikhail Khodak, Nicholas Roberts, Ameet Talwalkar
2021	A*	`conf`	Rethinking Neural Operations for Diverse Tasks. NeurIPS Nicholas Roberts, Mikhail Khodak, Tri Dao, Liam Li, Christopher Ré, Ameet Talwalkar
2021	J	`jnl`	Rethinking Neural Operations for Diverse Tasks. CoRR Nicholas Roberts, Mikhail Khodak, Tri Dao, Liam Li, Christopher Ré, Ameet Talwalkar
2020	A*	`conf`	A Sample Complexity Separation between Non-Convex and Convex Meta-Learning. ICML Nikunj Saunshi, Yi Zhang, Mikhail Khodak, Sanjeev Arora
2020	J	`jnl`	A Sample Complexity Separation between Non-Convex and Convex Meta-Learning. CoRR Nikunj Saunshi, Yi Zhang, Mikhail Khodak, Sanjeev Arora
2020	A*	`conf`	Differentially Private Meta-Learning. ICLR Jeffrey Li, Mikhail Khodak, Sebastian Caldas, Ameet Talwalkar
2020	J	`jnl`	Geometry-Aware Gradient Algorithms for Neural Architecture Search. CoRR Liam Li, Mikhail Khodak, Maria-Florina Balcan, Ameet Talwalkar
2019	A*	`conf`	A Theoretical Analysis of Contrastive Unsupervised Representation Learning. ICML Nikunj Saunshi, Orestis Plevrakis, Sanjeev Arora, Mikhail Khodak, Hrishikesh Khandeparkar
2019	J	`jnl`	A Theoretical Analysis of Contrastive Unsupervised Representation Learning. CoRR Sanjeev Arora, Hrishikesh Khandeparkar, Mikhail Khodak, Orestis Plevrakis, Nikunj Saunshi
2019	A*	`conf`	Adaptive Gradient-Based Meta-Learning Methods. NeurIPS Mikhail Khodak, Maria-Florina Balcan, Ameet Talwalkar
2019	J	`jnl`	Adaptive Gradient-Based Meta-Learning Methods. CoRR Mikhail Khodak, Maria-Florina Balcan, Ameet Talwalkar
2019	J	`jnl`	Advances and Open Problems in Federated Learning. CoRR Peter Kairouz, H. Brendan McMahan, Brendan Avent, Aurélien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Kallista A. Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, Rafael G. L. D'Oliveira, Salim El Rouayheb, David Evans, Josh Gardner, Zachary Garrett, Adrià Gascón, Badih Ghazi, Phillip B. Gibbons, Marco Gruteser, Zaïd Harchaoui, Chaoyang He, Lie He, Zhouyuan Huo, Ben Hutchinson, Justin Hsu, Martin Jaggi, Tara Javidi, Gauri Joshi, Mikhail Khodak, Jakub Konecný, Aleksandra Korolova, Farinaz Koushanfar, Sanmi Koyejo, Tancrède Lepoint, Yang Liu, Prateek Mittal, Mehryar Mohri, Richard Nock, Ayfer Özgür, Rasmus Pagh, Mariana Raykova, Hang Qi, Daniel Ramage, Ramesh Raskar, Dawn Song, Weikang Song, Sebastian U. Stich, Ziteng Sun, Ananda Theertha Suresh, Florian Tramèr, Praneeth Vepakomma, Jianyu Wang, Li Xiong, Zheng Xu, Qiang Yang, Felix X. Yu, Han Yu, Sen Zhao
2019	J	`jnl`	Differentially Private Meta-Learning. CoRR Jeffrey Li, Mikhail Khodak, Sebastian Caldas, Ameet Talwalkar
2019	A*	`conf`	Provable Guarantees for Gradient-Based Meta-Learning. ICML Maria-Florina Balcan, Mikhail Khodak, Ameet Talwalkar
2019	J	`jnl`	Provable Guarantees for Gradient-Based Meta-Learning. CoRR Mikhail Khodak, Maria-Florina Balcan, Ameet Talwalkar
2018	—	`conf`	A Compressed Sensing View of Unsupervised Text Embeddings, Bag-of-n-Grams, and LSTMs. ICLR (Poster) Sanjeev Arora, Mikhail Khodak, Nikunj Saunshi, Kiran Vodrahalli
2018	—	`conf`	A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors. ACL (1) Mikhail Khodak, Nikunj Saunshi, Yingyu Liang, Tengyu Ma, Brandon Stewart, Sanjeev Arora
2018	J	`jnl`	A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors. CoRR Mikhail Khodak, Nikunj Saunshi, Yingyu Liang, Tengyu Ma, Brandon Stewart, Sanjeev Arora
2018	B	`conf`	A Large Self-Annotated Corpus for Sarcasm. LREC Mikhail Khodak, Nikunj Saunshi, Kiran Vodrahalli
2018	A*	`conf`	Learning Cloud Dynamics to Optimize Spot Instance Bidding Strategies. INFOCOM Mikhail Khodak, Liang Zheng, Andrew S. Lan, Carlee Joe-Wong, Mung Chiang
2017	J	`jnl`	A Large Self-Annotated Corpus for Sarcasm. CoRR Mikhail Khodak, Nikunj Saunshi, Kiran Vodrahalli
2017	J	`jnl`	Extending and Improving Wordnet via Unsupervised Word Embeddings. CoRR Mikhail Khodak, Andrej Risteski, Christiane Fellbaum, Sanjeev Arora