Hanin, Boris

18 publications

NeurIPS 2025 Don't Be Lazy: CompleteP Enables Compute-Efficient Deep Transformers Nolan Simran Dey, Bin Claire Zhang, Lorenzo Noci, Mufan Li, Blake Bordelon, Shane Bergsma, Cengiz Pehlevan, Boris Hanin, Joel Hestness

ICLR 2025 Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization Noam Razin, Sadhika Malladi, Adithya Bhaskar, Danqi Chen, Sanjeev Arora, Boris Hanin

NeurIPS 2024 Are More LLM Calls All You Need? Towards the Scaling Properties of Compound AI Systems Lingjiao Chen, Jared Davis, Boris Hanin, Peter Bailis, Ion Stoica, Matei Zaharia, James Zou

ICLR 2024 Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit Blake Bordelon, Lorenzo Noci, Mufan Bill Li, Boris Hanin, Cengiz Pehlevan

ICLR 2024 Principled Architecture-Aware Scaling of Hyperparameters Wuyang Chen, Junru Wu, Zhangyang Wang, Boris Hanin

JMLR 2024 Random Fully Connected Neural Networks as Perturbatively Solvable Hierarchies Boris Hanin

NeurIPSW 2024 Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization Noam Razin, Sadhika Malladi, Adithya Bhaskar, Danqi Chen, Sanjeev Arora, Boris Hanin

NeurIPSW 2024 Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization Noam Razin, Sadhika Malladi, Adithya Bhaskar, Danqi Chen, Sanjeev Arora, Boris Hanin

NeurIPSW 2023 Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit Blake Bordelon, Lorenzo Noci, Mufan Li, Boris Hanin, Cengiz Pehlevan

ICML 2023 Maximal Initial Learning Rates in Deep ReLU Networks Gaurav Iyer, Boris Hanin, David Rolnick

NeurIPS 2022 Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis Wuyang Chen, Wei Huang, Xinyu Gong, Boris Hanin, Zhangyang Wang

ICLR 2022 Deep ReLU Networks Preserve Expected Length Boris Hanin, Ryan Jeong, David Rolnick

NeurIPS 2021 How Data Augmentation Affects Optimization for Linear Regression Boris Hanin, Yi Sun

ICLR 2020 Finite Depth and Width Corrections to the Neural Tangent Kernel Boris Hanin, Mihai Nica

ICML 2019 Complexity of Linear Regions in Deep Networks Boris Hanin, David Rolnick

NeurIPS 2019 Deep ReLU Networks Have Surprisingly Few Activation Patterns Boris Hanin, David Rolnick

NeurIPS 2018 How to Start Training: The Effect of Initialization and Architecture Boris Hanin, David Rolnick

NeurIPS 2018 Which Neural Net Architectures Give Rise to Exploding and Vanishing Gradients? Boris Hanin