
Private Stochastic Convex Optimization: Optimal Rates in ℓ_1 Geometry
Stochastic convex optimization over an ℓ_1bounded domain is ubiquitous ...
read it

Online Policy Gradient for Model Free Learning of Linear Quadratic Regulators with √(T) Regret
We consider the task of learning to control a linear dynamical system un...
read it

Multiplicative Reweighting for Robust Neural Network Optimization
Deep neural networks are widespread due to their powerful performance. Y...
read it

Lazy OCO: Online Convex Optimization on a Switching Budget
We study a variant of online convex optimization where the player is per...
read it

The Instability of Accelerated Gradient Descent
We study the algorithmic stability of Nesterov's accelerated gradient me...
read it

SGD Generalizes Better Than GD (And Regularization Doesn't Help)
We give a new separation result between the generalization performance o...
read it

Online Markov Decision Processes with Aggregate Bandit Feedback
We study a novel variant of online finitehorizon Markov Decision Proces...
read it

Adversarial Dueling Bandits
We introduce the problem of regret minimization in Adversarial Dueling B...
read it

Stochastic Optimization with Laggard Data Pipelines
Stateoftheart optimization is steadily shifting towards massively par...
read it

Holdout SGD: Byzantine Tolerant Federated Learning
This work presents a new distributed Byzantine tolerant federated learni...
read it

Bandit Linear Control
We consider the problem of controlling a known linear dynamical system u...
read it

Private Stochastic Convex Optimization: Optimal Rates in Linear Time
We study differentially private (DP) algorithms for stochastic convex op...
read it

Can Implicit Bias Explain Generalization? Stochastic Convex Optimization as a Case Study
The notion of implicit bias, or implicit regularization, has been sugges...
read it

Disentangling Adaptive Gradient Methods from Learning Rates
We investigate several confounding factors in the evaluation of optimiza...
read it

Prediction with Corrupted Expert Advice
We revisit the fundamental problem of prediction with expert advice, in ...
read it

Second Order Optimization Made Practical
Optimization in machine learning, both theoretical and applied, is prese...
read it

Logarithmic Regret for Learning Linear Quadratic Regulators Efficiently
We consider the problem of learning in Linear Quadratic Control systems ...
read it

Robust BiTempered Logistic Loss Based on Bregman Divergences
We introduce a temperature into the exponential function and replace the...
read it

SemiCyclic Stochastic Gradient Descent
We consider convex SGD updates with a blockcyclic structure, i.e. where...
read it

Better Algorithms for Stochastic Bandits with Adversarial Corruptions
We study the stochastic multiarmed bandits problem in the presence of a...
read it

Learning LinearQuadratic Regulators Efficiently with only √(T) Regret
We present the first computationallyefficient algorithm with O(√(T)) r...
read it

MemoryEfficient Adaptive Optimization for LargeScale Learning
Adaptive gradientbased optimizers such as AdaGrad and Adam are among th...
read it

Online Linear Quadratic Control
We study the problem of controlling linear timeinvariant systems with k...
read it

Shampoo: Preconditioned Stochastic Tensor Optimization
Preconditioned gradient methods are among the most general and powerful ...
read it

A Unified Approach to Adaptive Regularization in Online and Stochastic Optimization
We describe a framework for deriving and analyzing online optimization a...
read it

Online Learning with Feedback Graphs Without the Graphs
We study an online learning framework introduced by Mannor and Shamir (2...
read it

Linear Regression with Limited Observation
We consider the most common variants of linear regression, including Rid...
read it
Tomer Koren
is this you? claim profile