Training algorithms, broadly construed, are an essential part of every d...
We study the sample complexity of reducing reinforcement learning to a
s...
We consider the fundamental problem of online control of a linear dynami...
In this work, we consider the problem of collaborative multi-user
reinfo...
Very little is known about the training dynamics of adaptive gradient me...
We revisit the classical online portfolio selection problem. It is widel...
Mechanical ventilation is one of the most widely used therapies in the I...
Q-learning is a popular Reinforcement Learning (RL) algorithm which is w...
We introduce the multi-dimensional Skellam mechanism, a discrete differe...
Multiclass logistic regression is a fundamental task in machine learning...
When balancing the practical tradeoffs of iterative methods for large-sc...
We consider the setting of iterative learning control, or model-based po...
We present an open-source library of natively differentiable physics and...
We consider the problem of controlling an invasive mechanical ventilator...
State-of-the-art optimization is steadily shifting towards massively par...
We investigate several confounding factors in the evaluation of optimiza...
We study the role of depth in training randomly initialized overparamete...
We study optimal regret bounds for control in linear dynamical systems u...
We propose a framework of boosting for learning and control in environme...
Anahita is an autonomous underwater vehicle which is currently being
dev...
We study the control of a linear dynamical system with adversarial
distu...
State-of-the-art models are now trained with billions of parameters, rea...
Adaptive regularization methods come in diagonal and full-matrix variant...
Distributed stochastic gradient descent is an important subroutine in
di...
We investigate the role of the effective (a.k.a. statistical) dimension ...
Given a matrix A∈R^n× d and a vector b
∈R^d, we show how to compute an ϵ...
State-of-the-art methods in convex and non-convex optimization employ
hi...
We design differentially private algorithms for the problem of online li...
We design a non-convex second-order optimization algorithm that is guara...
First-order stochastic methods are the state-of-the-art in large-scale
m...
We consider the problem of identifying underlying community-like structu...