Boris Hanin - RankMe

51 papers A* 13Journal 38

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Hyperparameter Transfer with Mixture-of-Expert Layers. CoRR Tianze Jiang, Blake Bordelon, Cengiz Pehlevan, Boris Hanin
2025	J	`jnl`	BARE: Combining Base and Instruction-Tuned Language Models for Better Synthetic Data Generation. CoRR Alan Zhu, Parth Asawa, Jared Quincy Davis, Lingjiao Chen, Boris Hanin, Ion Stoica, Joseph E. Gonzalez, Matei Zaharia
2025	J	`jnl`	Deep Nets as Hamiltonians. CoRR Mike Winer, Boris Hanin
2025	J	`jnl`	Don't be lazy: CompleteP enables compute-efficient deep transformers. CoRR Nolan Dey, Bin Claire Zhang, Lorenzo Noci, Mufan Bill Li, Blake Bordelon, Shane Bergsma, Cengiz Pehlevan, Boris Hanin, Joel Hestness
2025	J	`jnl`	Implicit Bias of the JKO Scheme. CoRR Peter Halmos, Boris Hanin
2025	J	`jnl`	Optimizing Model Selection for Compound AI Systems. CoRR Lingjiao Chen, Jared Quincy Davis, Boris Hanin, Peter Bailis, Matei Zaharia, James Zou, Ion Stoica
2025	J	`jnl`	Principles for Initialization and Architecture Selection in Graph Neural Networks with ReLU Activations. SIAM J. Math. Data Sci. Gage DeZoort, Boris Hanin
2025	J	`jnl`	The Future of Artificial Intelligence and the Mathematical and Physical Sciences (AI+MPS). CoRR Andrew Ferguson, Marisa Lafleur, Lars Ruthotto, Jesse Thaler, Yuan-Sen Ting, Pratyush Tiwary, Soledad Villar, E. Paulo Alves, Jeremy Avigad, Simon Billinge, Camille L. Bilodeau, Keith Brown, Emmanuel J. Candès, Arghya Chattopadhyay, Bingqing Cheng, Jonathan Clausen, Connor W. Coley, Andrew J. Connolly, Fred Daum, Sijia S. Dong, Chrisy Xiyu Du, Cora Dvorkin, Cristiano Fanelli, Eric B. Ford, Luis Manuel Frutos, Nicolás García Trillos, Cecilia Garraffo, Robert Ghrist, Rafael Gómez-Bombarelli, Gianluca Guadagni, Sreelekha Guggilam, Sergei Gukov, Juan B. Gutierrez, Salman Habib, Johannes Hachmann, Boris Hanin, Philip C. Harris, Murray Holland, Elizabeth Holm, Hsin-Yuan Huang, Shih-Chieh Hsu, Nick Jackson, Olexandr Isayev, Heng Ji, Aggelos K. Katsaggelos, Jeremy Kepner, Yannis G. Kevrekidis, Michelle P. Kuchera, J. Nathan Kutz, Branislava Lalic, Ann Lee, Matt LeBlanc, Josiah Lim, Rebecca Lindsey, Yongmin Liu, Peter Y. Lu, Sudhir Malik, Vuk Mandic, Vidya B. Manian, Emeka P. Mazi, Pankaj Mehta, Peter Melchior, Brice Ménard, Jennifer Ngadiuba, Stella Offner, Elsa Olivetti, Shyue Ping Ong, Christopher Rackauckas, Philippe Rigollet, Chad Risko, Philip Romero, Grant M. Rotskoff, Brett Savoie, Uros Seljak, David Shih, Gary Shiu, Dima Shlyakhtenko, Eva Silverstein, Taylor Sparks, Thomas Strohmer, Christopher Stubbs, Stephen Thomas, Suriyanarayanan Vaikuntanathan, René Vidal, Francisco Villaescusa-Navarro, Gregory Voth, Benjamin Wandelt, Rachel Ward, Melanie Weber, Risa Wechsler, Stephen Whitelam, Olaf Wiest, Mike Williams, Zhuoran Yang, Yaroslava G. Yingling, Bin Yu, Shuwen Yue, Ann Zabludoff, Huimin Zhao, Tong Zhang
2025	A*	`conf`	Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization. ICLR Noam Razin, Sadhika Malladi, Adithya Bhaskar, Danqi Chen, Sanjeev Arora, Boris Hanin
2024	J	`jnl`	Are More LLM Calls All You Need? Towards Scaling Laws of Compound Inference Systems. CoRR Lingjiao Chen, Jared Quincy Davis, Boris Hanin, Peter Bailis, Ion Stoica, Matei Zaharia, James Zou
2024	A*	`conf`	Are More LLM Calls All You Need? Towards the Scaling Properties of Compound AI Systems. NeurIPS Lingjiao Chen, Jared Quincy Davis, Boris Hanin, Peter Bailis, Ion Stoica, Matei A. Zaharia, James Y. Zou
2024	J	`jnl`	Bayesian Inference with Deep Weakly Nonlinear Networks. CoRR Boris Hanin, Alexander Zlokapa
2024	A*	`conf`	Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit. ICLR Blake Bordelon, Lorenzo Noci, Mufan Bill Li, Boris Hanin, Cengiz Pehlevan
2024	J	`jnl`	Networks of Networks: Complexity Class Principles Applied to Compound AI Systems Design. CoRR Jared Quincy Davis, Boris Hanin, Lingjiao Chen, Peter Bailis, Ion Stoica, Matei Zaharia
2024	A*	`conf`	Principled Architecture-aware Scaling of Hyperparameters. ICLR Wuyang Chen, Junru Wu, Zhangyang Wang, Boris Hanin
2024	J	`jnl`	Principled Architecture-aware Scaling of Hyperparameters. CoRR Wuyang Chen, Junru Wu, Zhangyang Wang, Boris Hanin
2024	J	`jnl`	Random Fully Connected Neural Networks as Perturbatively Solvable Hierarchies. J. Mach. Learn. Res. Boris Hanin
2024	J	`jnl`	Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization. CoRR Noam Razin, Sadhika Malladi, Adithya Bhaskar, Danqi Chen, Sanjeev Arora, Boris Hanin
2023	J	`jnl`	Depth Dependence of μP Learning Rates in ReLU MLPs. CoRR Samy Jelassi, Boris Hanin, Ziwei Ji, Sashank J. Reddi, Srinadh Bhojanapalli, Sanjiv Kumar
2023	J	`jnl`	Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit. CoRR Blake Bordelon, Lorenzo Noci, Mufan Bill Li, Boris Hanin, Cengiz Pehlevan
2023	J	`jnl`	Les Houches Lectures on Deep Learning at Large & Infinite Width. CoRR Yasaman Bahri, Boris Hanin, Antonin Brossollet, Vittorio Erba, Christian Keup, Rosalba Pacelli, James B. Simon
2023	A*	`conf`	Maximal Initial Learning Rates in Deep ReLU Networks. ICML Gaurav Iyer, Boris Hanin, David Rolnick
2023	J	`jnl`	Principles for Initialization and Architecture Selection in Graph Neural Networks with ReLU Activations. CoRR Gage DeZoort, Boris Hanin
2023	J	`jnl`	Quantitative CLTs in Deep Neural Networks. CoRR Stefano Favaro, Boris Hanin, Domenico Marinucci, Ivan Nourdin, Giovanni Peccati
2022	J	`jnl`	Bayesian Interpolation with Deep Linear Networks. CoRR Boris Hanin, Alexander Zlokapa
2022	J	`jnl`	Correlation Functions in Random Fully Connected Neural Networks at Finite Width. CoRR Boris Hanin
2022	A*	`conf`	Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis. NeurIPS Wuyang Chen, Wei Huang, Xinyu Gong, Boris Hanin, Zhangyang Wang
2022	J	`jnl`	Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis. CoRR Wuyang Chen, Wei Huang, Xinyu Gong, Boris Hanin, Zhangyang Wang
2022	A*	`conf`	Deep ReLU Networks Preserve Expected Length. ICLR Boris Hanin, Ryan S. Jeong, David Rolnick
2022	J	`jnl`	Maximal Initial Learning Rates in Deep ReLU Networks. CoRR Gaurav Iyer, Boris Hanin, David Rolnick
2021	J	`jnl`	Deep ReLU Networks Preserve Expected Length. CoRR Boris Hanin, Ryan Jeong, David Rolnick
2021	A*	`conf`	How Data Augmentation affects Optimization for Linear Regression. NeurIPS Boris Hanin, Yi Sun
2021	J	`jnl`	Neural network approximation. Acta Numer. Ronald A. DeVore, Boris Hanin, Guergana Petrova
2021	J	`jnl`	Random Neural Networks in the Infinite Width Limit as Gaussian Processes. CoRR Boris Hanin
2021	J	`jnl`	Ridgeless Interpolation with Shallow ReLU Networks in $1D$ is Nearest Neighbor Curvature Extrapolation and Provably Generalizes on Lipschitz Functions. CoRR Boris Hanin
2021	J	`jnl`	The Principles of Deep Learning Theory. CoRR Daniel A. Roberts, Sho Yaida, Boris Hanin
2020	J	`jnl`	Data augmentation as stochastic optimization. CoRR Boris Hanin, Yi Sun
2020	A*	`conf`	Finite Depth and Width Corrections to the Neural Tangent Kernel. ICLR Boris Hanin, Mihai Nica
2020	J	`jnl`	Neural Network Approximation. CoRR Ronald A. DeVore, Boris Hanin, Guergana Petrova
2019	A*	`conf`	Complexity of Linear Regions in Deep Networks. ICML Boris Hanin, David Rolnick
2019	J	`jnl`	Complexity of Linear Regions in Deep Networks. CoRR Boris Hanin, David Rolnick
2019	A*	`conf`	Deep ReLU Networks Have Surprisingly Few Activation Patterns. NeurIPS Boris Hanin, David Rolnick
2019	J	`jnl`	Deep ReLU Networks Have Surprisingly Few Activation Patterns. CoRR Boris Hanin, David Rolnick
2019	J	`jnl`	Finite Depth and Width Corrections to the Neural Tangent Kernel. CoRR Boris Hanin, Mihai Nica
2019	J	`jnl`	Nonlinear Approximation and (Deep) ReLU Networks. CoRR Ingrid Daubechies, Ronald A. DeVore, Simon Foucart, Boris Hanin, Guergana Petrova
2018	A*	`conf`	How to Start Training: The Effect of Initialization and Architecture. NeurIPS Boris Hanin, David Rolnick
2018	J	`jnl`	How to Start Training: The Effect of Initialization and Architecture. CoRR Boris Hanin, David Rolnick
2018	J	`jnl`	Which Neural Net Architectures Give Rise To Exploding and Vanishing Gradients? CoRR Boris Hanin
2018	A*	`conf`	Which Neural Net Architectures Give Rise to Exploding and Vanishing Gradients? NeurIPS Boris Hanin
2017	J	`jnl`	Approximating Continuous Functions by ReLU Nets of Minimal Width. CoRR Boris Hanin, Mark Sellke
2017	J	`jnl`	Universal Function Approximation by Deep Neural Nets with Bounded Width and ReLU Activations. CoRR Boris Hanin