Jeremy Bernstein

Publication Activity (10 Years)

Years Active: 2017-2024
Publications (10 Years): 27

Top Topics

Trained Neural Networks

Top Venues

Publications

Fredrik Heiding, Bruce Schneier, Arun Vishwanath, Jeremy Bernstein, Peter S. Park
Devising and Detecting Phishing Emails Using Large Language Models. IEEE Access 12 (2024)
Minyoung Huh, Brian Cheung, Jeremy Bernstein, Phillip Isola, Pulkit Agrawal
Training Neural Networks from Scratch with Parallel Low-Rank Adapters. CoRR (2024)
Tim Large, Yang Liu, Minyoung Huh, Hyojin Bahng, Phillip Isola, Jeremy Bernstein
Scalable Optimization in the Modular Norm. CoRR (2024)
Benjamin Wright, Youngjae Min, Jeremy Bernstein, Navid Azizan
SketchOGD: Memory-Efficient Continual Learning. CoRR (2023)
Fredrik Heiding, Bruce Schneier, Arun Vishwanath, Jeremy Bernstein
Devising and Detecting Phishing: Large Language Models vs. Smaller Human Models. CoRR (2023)
Greg Yang, James B. Simon, Jeremy Bernstein
A Spectral Condition for Feature Learning. CoRR (2023)
Jeremy Bernstein, Chris Mingard, Kevin Huang, Navid Azizan, Yisong Yue
Automatic Gradient Descent: Deep Learning without Hyperparameters. CoRR (2023)
Alexander R. Farhang, Jeremy Bernstein, Kushal Tirumala, Yang Liu, Yisong Yue
Investigating Generalization by Controlling Normalized Margin. CoRR (2022)
Jeremy Bernstein
Optimisation & Generalisation in Networks of Neurons. CoRR (2022)
Jeremy Bernstein, Yisong Yue
Computing the Information Content of Trained Neural Networks. CoRR (2021)
Dawna Bagherian, James Gornet, Jeremy Bernstein, Yu-Li Ni, Yisong Yue, Markus Meister
Fine-Grained System Identification of Nonlinear Neural Circuits. CoRR (2021)
Yang Liu, Jeremy Bernstein, Markus Meister, Yisong Yue
Learning by Turning: Neural Architecture Aware Optimisation. ICML (2021)
Yang Liu, Jeremy Bernstein, Markus Meister, Yisong Yue
Learning by Turning: Neural Architecture Aware Optimisation. CoRR (2021)
Dawna Bagherian, James Gornet, Jeremy Bernstein, Yu-Li Ni, Yisong Yue, Markus Meister
Fine-Grained System Identification of Nonlinear Neural Circuits. KDD (2021)
Jeremy Bernstein, Yisong Yue
On the Implicit Biases of Architecture & Gradient Descent. CoRR (2021)
Jeremy Bernstein, Jiawei Zhao, Markus Meister, Ming-Yu Liu, Anima Anandkumar, Yisong Yue
Learning compositional functions via multiplicative weight updates. CoRR (2020)
Jeremy Bernstein, Jiawei Zhao, Markus Meister, Ming-Yu Liu, Anima Anandkumar, Yisong Yue
Learning compositional functions via multiplicative weight updates. NeurIPS (2020)
Jeremy Bernstein, Arash Vahdat, Yisong Yue, Ming-Yu Liu
On the distance between two neural networks and the stability of learning. CoRR (2020)
Jeremy Bernstein, Arash Vahdat, Yisong Yue, Ming-Yu Liu
On the distance between two neural networks and the stability of learning. NeurIPS (2020)
Jeremy Bernstein, Jiawei Zhao, Kamyar Azizzadenesheli, Anima Anandkumar
signSGD with Majority Vote is Communication Efficient and Fault Tolerant. ICLR (Poster) (2019)
Jeremy Bernstein, Yu-Xiang Wang, Kamyar Azizzadenesheli, Anima Anandkumar
signSGD: compressed optimisation for non-convex problems. CoRR (2018)
Guneet S. Dhillon, Kamyar Azizzadenesheli, Zachary C. Lipton, Jeremy Bernstein, Jean Kossaifi, Aran Khanna, Anima Anandkumar
Stochastic Activation Pruning for Robust Adversarial Defense. CoRR (2018)
Jeremy Bernstein, Yu-Xiang Wang, Kamyar Azizzadenesheli, Anima Anandkumar
Compression by the signs: distributed learning is a two-way street. ICLR (Workshop) (2018)
Jeremy Bernstein, Jiawei Zhao, Kamyar Azizzadenesheli, Anima Anandkumar
signSGD with Majority Vote is Communication Efficient And Byzantine Fault Tolerant. CoRR (2018)
Guneet S. Dhillon, Kamyar Azizzadenesheli, Zachary C. Lipton, Jeremy Bernstein, Jean Kossaifi, Aran Khanna, Animashree Anandkumar
Stochastic Activation Pruning for Robust Adversarial Defense. ICLR (Poster) (2018)
Jeremy Bernstein, Yu-Xiang Wang, Kamyar Azizzadenesheli, Animashree Anandkumar
SIGNSGD: Compressed Optimisation for Non-Convex Problems. ICML (2018)
Jeremy Bernstein, Ishita Dasgupta, David Rolnick, Haim Sompolinsky
Markov Transitions between Attractor States in a Recurrent Neural Network. AAAI Spring Symposia (2017)