Jeremy Bernstein

According to our database, Jeremy Bernstein authored at least 22 papers between 2017 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2024

Old Optimizer, New Norm: An Anthology.

Jeremy Bernstein, Laker Newhouse

CoRR, 2024

Scalable Optimization in the Modular Norm.

Tim Large, Yang Liu, Minyoung Huh, Hyojin Bahng, Phillip Isola, Jeremy Bernstein

CoRR, 2024

Training Neural Networks from Scratch with Parallel Low-Rank Adapters.

Minyoung Huh, Brian Cheung, Jeremy Bernstein, Phillip Isola, Pulkit Agrawal

CoRR, 2024

Devising and Detecting Phishing Emails Using Large Language Models.

Fredrik Heiding, Bruce Schneier, Arun Vishwanath, Jeremy Bernstein, Peter S. Park

IEEE Access, 2024

2023

A Spectral Condition for Feature Learning.

Greg Yang, James B. Simon, Jeremy Bernstein

CoRR, 2023

Devising and Detecting Phishing: Large Language Models vs. Smaller Human Models.

Fredrik Heiding, Bruce Schneier, Arun Vishwanath, Jeremy Bernstein

CoRR, 2023

SketchOGD: Memory-Efficient Continual Learning.

Benjamin Wright, Youngjae Min, Jeremy Bernstein, Navid Azizan

CoRR, 2023

Automatic Gradient Descent: Deep Learning without Hyperparameters.

Jeremy Bernstein, Chris Mingard, Kevin Huang, Navid Azizan, Yisong Yue

CoRR, 2023

2022

Optimisation & Generalisation in Networks of Neurons.

Jeremy Bernstein

CoRR, 2022

Investigating Generalization by Controlling Normalized Margin.

Alexander R. Farhang, Jeremy D. Bernstein, Kushal Tirumala, Yang Liu, Yisong Yue

Proceedings of the International Conference on Machine Learning, 2022

2021

On the Implicit Biases of Architecture & Gradient Descent.

Jeremy Bernstein, Yisong Yue

CoRR, 2021

Computing the Information Content of Trained Neural Networks.

Jeremy Bernstein, Yisong Yue

CoRR, 2021

Fine-Grained System Identification of Nonlinear Neural Circuits.

Dawna Bagherian, James Gornet, Jeremy Bernstein, Yu-Li Ni, Yisong Yue, Markus Meister

Proceedings of the KDD '21: The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2021

Learning by Turning: Neural Architecture Aware Optimisation.

Yang Liu, Jeremy Bernstein, Markus Meister, Yisong Yue

Proceedings of the 38th International Conference on Machine Learning, 2021

2020

Learning compositional functions via multiplicative weight updates.

Jeremy Bernstein, Jiawei Zhao, Markus Meister, Ming-Yu Liu, Anima Anandkumar, Yisong Yue

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

On the distance between two neural networks and the stability of learning.

Jeremy Bernstein, Arash Vahdat, Yisong Yue, Ming-Yu Liu

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

2019

signSGD with Majority Vote is Communication Efficient and Fault Tolerant.

Jeremy Bernstein, Jiawei Zhao, Kamyar Azizzadenesheli, Anima Anandkumar

Proceedings of the 7th International Conference on Learning Representations, 2019

2018

signSGD with Majority Vote is Communication Efficient And Byzantine Fault Tolerant.

Jeremy Bernstein, Jiawei Zhao, Kamyar Azizzadenesheli, Anima Anandkumar

CoRR, 2018

SIGNSGD: Compressed Optimisation for Non-Convex Problems.

Jeremy Bernstein, Yu-Xiang Wang, Kamyar Azizzadenesheli, Animashree Anandkumar

Proceedings of the 35th International Conference on Machine Learning, 2018

Stochastic Activation Pruning for Robust Adversarial Defense.

Guneet S. Dhillon, Kamyar Azizzadenesheli, Zachary C. Lipton, Jeremy Bernstein, Jean Kossaifi, Aran Khanna, Animashree Anandkumar

Proceedings of the 6th International Conference on Learning Representations, 2018

Compression by the signs: distributed learning is a two-way street.

Jeremy Bernstein, Yu-Xiang Wang, Kamyar Azizzadenesheli, Anima Anandkumar

Proceedings of the 6th International Conference on Learning Representations, 2018

2017

Markov Transitions between Attractor States in a Recurrent Neural Network.

Jeremy Bernstein, Ishita Dasgupta, David Rolnick, Haim Sompolinsky

Proceedings of the 2017 AAAI Spring Symposia, 2017