Blake Woodworth
Professor Blake Woodworth's research studies the theory of optimization and machine learning. On the optimization side, he focuses on distributed algorithms for large-scale stochastic optimization problems, especially training machine learning models. On the machine learning side, he is interested in understanding the how and why highly overparametrized models like deep neural networks are able to generalize as well as they do in practice.
- Two Losses Are Better Than One: Faster Optimization Using a Cheaper Proxy
Blake Woodworth, Konstantin Mishchenko, Francis Bach
ICML, 2023
- Asynchronous SGD Beats Minibatch SGD Under Arbitrary Delays
Konstantin Mishchenko, Francis Bach, Mathieu Even, Blake Woodworth
NeurIPS, 2022
- Non-Convex Optimization with Certificates and Fast Rates Through Kernel Sums of Squares
Blake Woodworth, Francis Bach, Alessandro Rudi
COLT, 2022
- Lower Bounds for Non-Convex Stochastic Optimization
Yossi Arjevani, Yair Carmon, John C. Duchi, Dylan J. Foster, Nathan Srebro, Blake Woodworth
Mathematical Programming, 2022
arXiv version
- The Minimax Complexity of Distributed Optimization
Blake Woodworth
PhD Thesis, 2021
- A Stochastic Newton Algorithm for Distributed Convex Optimization
Brian Bullins, Kumar Kshitij Patel, Ohad Shamir, Nathan Srebro, Blake Woodworth
NeurIPS, 2021
- An Even More Optimal Stochastic Optimization Algorithm: Minibatching and Interpolation Learning
Blake Woodworth, Nathan Srebro
NeurIPS, 2021
- On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent
Shahar Azulay, Edward Moroshko, Mor Shpigel Nacson, Blake Woodworth, Nathan Srebro, Amir Globerson, Daniel Soudry
ICML, 2021
- The Min-Max Complexity of Distributed Stochastic Convex Optimization with Intermittent Communication
Blake Woodworth, Brian Bullins, Ohad Shamir, Nathan Srebro
Best Paper Award
COLT, 2021
- Mirrorless Mirror Descent: A More Natural Discretization of Riemannian Gradient Flow
Suriya Gunasekar, Blake Woodworth, Nathan Srebro
AISTATS, 2021
- Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy
Edward Moroshko, Suriya Gunasekar, Blake Woodworth, Jason D. Lee, Nathan Srebro, Daniel Soudry
NeurIPS, 2020
- Minibatch vs Local SGD for Heterogeneous Distributed Learning
Blake Woodworth, Kumar Kshitij Patel, Nathan Srebro
NeurIPS, 2020
- Is Local SGD Better than Minibatch SGD?
Blake Woodworth, Kumar Kshitij Patel, Sebastian U. Stich, Zhen Dai, Brian Bullins, H. Brendan McMahan, Ohad Shamir, Nathan Srebro
ICML, 2020
Python code
- Kernel and Deep Regimes in Overparametrized Models
Blake Woodworth, Suriya Gunasekar, Jason D. Lee, Edward Moroshko, Pedro Savarese, Itay Golan, Daniel Soudry, Nathan Srebro
COLT, 2020
- The Gradient Complexity of Linear Regression
Mark Braverman, Elad Hazan, Max Simchowitz, Blake Woodworth
COLT, 2020
- Guaranteed Validity for Empirical Approaches to Adaptive Data Analysis
Ryan Rogers, Aaron Roth, Adam Smith, Nathan Srebro, Om Thakkar, Blake Woodworth
AISTATS, 2020
- Open Problem: The Oracle Complexity of Convex Optimization with Limited Memory
Blake Woodworth, Nathan Srebro
COLT, 2019
- The Complexity of Making the Gradient Small in Stochastic Convex Optimization
Dylan Foster, Ayush Sekhari, Ohad Shamir, Nathan Srebro, Karthik Sridharan, Blake Woodworth
Best Student Paper Award
COLT, 2019
- Graph Oracle Models, Lower Bounds, and Gaps for Parallel Stochastic Optimization
Blake Woodworth, Jialei Wang, Adam Smith, Brendan McMahan, and Nathan Srebro
NeurIPS, 2018
- Training Well-Generalizing Classifiers for Fairness Metrics and Other Data-Dependent Constraints
Andrew Cotter, Maya Gupta, Heinrich Jiang, Nathan Srebro, Karthik Sridharan, Serena Wang, Blake Woodworth, and Seungil You
FAT/ML 2018, ICML 2019
- The Everlasting Database: Statistical Validity at a Fair Price
Blake Woodworth, Vitaly Feldman, Saharon Rosset, and Nathan Srebro
NeurIPS, 2018
- Lower Bound for Randomized First Order Convex Optimization
Blake Woodworth and Nathan Srebro
arXiv, 2017
- Implicit Regularization in Matrix Factorization
Suriya Gunasekar, Blake Woodworth, Srinadh Bhojanapalli, Behnam Neyshabur, and Nathan Srebro
NeurIPS, 2017
- Learning Non-Discriminatory Predictors
Blake Woodworth, Suriya Gunasekar, Mesrob I. Ohannessian, and Nathan Srebro
COLT, 2017
- Tight Complexity Bounds for Optimizing Composite Objectives
Blake Woodworth and Nathan Srebro
NeurIPS, 2016