research
∙
08/20/2023
Improved Differentially Private Densest Subgraph: Local and Purely Additive
We study the Densest Subgraph problem under the additional constraint of...
share
research
∙
10/13/2022
From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent
Stochastic Gradient Descent (SGD) has been the method of choice for lear...
research
∙
07/06/2022
Private Matrix Approximation and Geometry of Unitary Orbits
Consider the following optimization problem: Given n × n matrices A and ...
research
∙
05/26/2022
Mixed Federated Learning: Joint Decentralized and Centralized Learning
Federated learning (FL) enables learning from decentralized privacy-sens...
research
∙
02/09/2022
Reproducibility in Optimization: Theoretical Framework and Limits
We initiate a formal study of reproducibility in optimization. We define...
research
∙
02/06/2022
Pushing the Efficiency-Regret Pareto Frontier for Online Learning of Portfolios and Quantum States
We revisit the classical online portfolio selection problem. It is widel...
research
∙
01/31/2022
Agnostic Learnability of Halfspaces via Logistic Loss
We investigate approximation guarantees provided by logistic regression ...
research
∙
10/06/2021
Efficient Methods for Online Multiclass Logistic Regression
Multiclass logistic regression is a fundamental task in machine learning...
research
∙
07/11/2021
SGD: The Role of Implicit Regularization, Batch-size and Multiple-epochs
Multi-epoch, small-batch, Stochastic Gradient Descent (SGD) has been the...
research
∙
03/01/2021
A Multiclass Boosting Framework for Achieving Fast and Provable Adversarial Robustness
Alongside the well-publicized accomplishments of deep neural networks th...
research
∙
02/23/2021
Learning with User-Level Privacy
We propose and analyze algorithms to solve a range of learning tasks und...
research
∙
08/08/2020
Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning
Federated learning is a challenging optimization problem due to the hete...
research
∙
02/19/2020
Estimating Training Data Influence by Tracking Gradient Descent
We introduce a method called TrackIn that computes the influence of a tr...
research
∙
02/04/2020
A Deep Conditioning Treatment of Neural Networks
We study the role of depth in training randomly initialized overparamete...
research
∙
10/14/2019
SCAFFOLD: Stochastic Controlled Averaging for On-Device Federated Learning
Federated learning is a key scenario in modern large-scale machine learn...
research
∙
04/19/2019
On the Convergence of Adam and Beyond
Several recently proposed stochastic optimization methods that have been...
research
∙
04/09/2019
Hypothesis Set Stability and Generalization
We present an extensive study of generalization for data-dependent hypot...
research
∙
01/26/2019
Escaping Saddle Points with Adaptive Gradient Methods
Adaptive methods such as Adam and RMSProp are widely used in deep learni...
research
∙
10/16/2018
Stochastic Negative Mining for Learning with Large Output Spaces
We consider the problem of retrieving the most relevant labels for a giv...
research
∙
03/25/2018
Logistic Regression: The Importance of Being Improper
Learning linear predictors with the logistic loss---both in stochastic a...
research
∙
12/30/2017
Parameter-free online learning via model selection
We introduce an efficient algorithmic framework for model selection in o...
research
∙
02/04/2014
Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits
We present a new algorithm for the contextual bandit learning problem, w...
research
∙
04/22/2013
Bargaining for Revenue Shares on Tree Trading Networks
We study trade networks with a tree structure, where a seller with a sin...
research
∙
06/27/2012
Efficient and Practical Stochastic Subgradient Descent for Nuclear Norm Regularization
We describe novel subgradient methods for a broad class of matrix optimi...
research
∙
06/13/2011