
A Regret Minimization Approach to Iterative Learning Control
We consider the setting of iterative learning control, or modelbased po...
read it

Deluca – A Differentiable Control Library: Environments, Methods, and Benchmarking
We present an opensource library of natively differentiable physics and...
read it

Boosting for Online Convex Optimization
We consider the decisionmaking framework of online convex optimization ...
read it

Machine Learning for Mechanical Ventilation Control
We consider the problem of controlling an invasive mechanical ventilator...
read it

Generating Adversarial Disturbances for Controller Verification
We consider the problem of generating maximally adversarial disturbances...
read it

Geometric Exploration for Online Control
We study the control of an unknown linear dynamical system under general...
read it

NonStochastic Control with Bandit Feedback
We study the problem of controlling a linear dynamical system with adver...
read it

Online Boosting with Bandit Feedback
We consider the problem of online boosting for regression tasks, when on...
read it

BlackBox Control for Linear Dynamical Systems
We consider the problem of controlling an unknown linear timeinvariant ...
read it

Adaptive Regret for Control of TimeVarying Dynamics
We consider regret minimization for online control with timevarying lin...
read it

Online Agnostic Boosting via Regret Minimization
Boosting is a widely used machine learning approach based on the idea of...
read it

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

Boosting Simple Learners
We consider boosting algorithms under the restriction that the weak lear...
read it

Faster Projectionfree Online Learning
In many online learning problems the computational bottleneck for gradie...
read it

Improper Learning for NonStochastic Control
We consider the problem of controlling a possibly unknown linear dynamic...
read it

The Nonstochastic Control Problem
We consider the problem of controlling an unknown linear dynamical syste...
read it

The gradient complexity of linear regression
We investigate the computational complexity of several basic linear alge...
read it

Logarithmic Regret for Online Control
We study optimal regret bounds for control in linear dynamical systems u...
read it

Lecture Notes: Optimization for Machine Learning
Lecture notes on optimization for machine learning, derived from a cours...
read it

Introduction to Online Convex Optimization
This manuscript portrays optimization as a process. In many practical ap...
read it

Boosting for Dynamical Systems
We propose a framework of boosting for learning and control in environme...
read it

Private Learning Implies Online Learning: An Efficient Reduction
We study the relationship between the notions of differentially private ...
read it

Online Control with Adversarial Disturbances
We study the control of a linear dynamical system with adversarial distu...
read it

Extreme Tensoring for LowMemory Preconditioning
Stateoftheart models are now trained with billions of parameters, rea...
read it

Exponentiated Gradient Meets Gradient Descent
The (stochastic) gradient descent and the multiplicative update method a...
read it

Provably Efficient Maximum Entropy Exploration
Suppose an agent is in a (possibly unknown) Markov decision process (MDP...
read it

Learning in Nonconvex Games with an Optimization Oracle
We consider adversarial online learning in a nonconvex setting under th...
read it

The Case for FullMatrix Adaptive Regularization
Adaptive regularization methods come in diagonal and fullmatrix variant...
read it

Online Improper Learning with an Approximation Oracle
We revisit the question of reducing online learning to approximate optim...
read it

Online Learning of Quantum States
Suppose we have many copies of an unknown nqubit state ρ. We measure so...
read it

On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization
Conventional wisdom in deep learning states that increasing depth improv...
read it

Spectral Filtering for General Linear Dynamical Systems
We give a polynomialtime algorithm for learning latentstate linear dyn...
read it

Learning Linear Dynamical Systems via Spectral Filtering
We present an efficient and practical algorithm for the online predictio...
read it

Lower Bounds for HigherOrder Convex Optimization
Stateoftheart methods in convex and nonconvex optimization employ hi...
read it

Linear Convergence of a FrankWolfe Type Algorithm over TraceNorm Balls
We propose a rankk variant of the classical FrankWolfe algorithm to so...
read it

Efficient Regret Minimization in NonConvex Games
We consider regret minimization in repeated games with nonconvex loss f...
read it

Hyperparameter Optimization: A Spectral Approach
We give a simple, fast algorithm for hyperparameter optimization inspire...
read it

Finding Approximate Local Minima Faster than Gradient Descent
We design a nonconvex secondorder optimization algorithm that is guara...
read it

A Nongenerative Framework and Convex Relaxations for Unsupervised Learning
We give a novel formal theoretical framework for unsupervised learning w...
read it

Variance Reduction for Faster NonConvex Optimization
We consider the fundamental problem in nonconvex optimization of effici...
read it

Optimal BlackBox Reductions Between Optimization Objectives
The diverse world of machine learning applications has given rise to a p...
read it

SecondOrder Stochastic Optimization for Machine Learning in Linear Time
Firstorder stochastic methods are the stateoftheart in largescale m...
read it

Volumetric Spanners: an Efficient Exploration Basis for Learning
Numerous machine learning problems require an exploration basis  a mech...
read it

A Linearly Convergent Conditional Gradient Algorithm with Applications to Online and Stochastic Optimization
Linear optimization is many times algorithmically simpler than nonlinea...
read it

Linear Regression with Limited Observation
We consider the most common variants of linear regression, including Rid...
read it

(weak) Calibration is Computationally Hard
We show that the existence of a computationally efficient calibration al...
read it