
-
Information Directed Reward Learning for Reinforcement Learning
For many reinforcement learning (RL) applications, specifying a reward i...
read it
-
Risk-Averse Offline Reinforcement Learning
Training Reinforcement Learning (RL) agents in high-stakes applications ...
read it
-
Efficient Pure Exploration for Combinatorial Bandits with Semi-Bandit Feedback
Combinatorial bandits with semi-bandit feedback generalize multi-armed b...
read it
-
Safe and Efficient Model-free Adaptive Control via Bayesian Optimization
Adaptive control approaches yield high-performance controllers when a pr...
read it
-
Incentive-Compatible Forecasting Competitions
We initiate the study of incentive-compatible forecasting competitions i...
read it
-
Logistic Q-Learning
We propose a new reinforcement learning algorithm derived from a regular...
read it
-
Online Active Model Selection for Pre-trained Classifiers
Given k pre-trained classifiers and a stream of unlabeled data examples,...
read it
-
Semi-supervised Batch Active Learning via Bilevel Optimization
Active learning is an effective technique for reducing the labeling cost...
read it
-
Rao-Blackwellizing the Straight-Through Gumbel-Softmax Gradient Estimator
Gradient estimation in models with discrete latent variables is a challe...
read it
-
Learning Set Functions that are Sparse in Non-Orthogonal Fourier Bases
Many applications of machine learning on discrete domains, such as learn...
read it
-
Learning to Play Sequential Games versus Unknown Opponents
We consider a repeated sequential game between a learner, who plays firs...
read it
-
Stochastic Linear Bandits Robust to Adversarial Attacks
We consider a stochastic linear bandit problem in which the rewards are ...
read it
-
Continuous Submodular Function Maximization
Continuous submodular functions are a category of generally non-convex/n...
read it
-
Learning Controllers for Unstable Linear Quadratic Regulators from a Single Trajectory
We present the first approach for learning – from a single trajectory – ...
read it
-
Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planning
Model-based reinforcement learning algorithms with probabilistic dynamic...
read it
-
Gradient Estimation with Stochastic Softmax Tricks
The Gumbel-Max trick is the basis of many relaxed gradient estimators. T...
read it
-
Learning Graph Models for Template-Free Retrosynthesis
Retrosynthesis prediction is a fundamental problem in organic synthesis,...
read it
-
Coresets via Bilevel Optimization for Continual Learning and Streaming
Coresets are small data summaries that are sufficient for model training...
read it
-
From Sets to Multisets: Provable Variational Inference for Probabilistic Integer Submodular Models
Submodular functions have been studied extensively in machine learning a...
read it
-
Hierarchical Image Classification using Entailment Cone Embeddings
Image classification has been studied extensively, but there has been li...
read it
-
SLEIPNIR: Deterministic and Provably Accurate Feature Expansion for Gaussian Process Regression with Derivatives
Gaussian processes are an important regression tool with excellent analy...
read it
-
Corruption-Tolerant Gaussian Process Bandit Optimization
We consider the problem of optimizing an unknown (typically non-convex) ...
read it
-
Mixed Strategies for Robust Optimization of Unknown Objectives
We consider robust optimization problems, where the goal is to optimize ...
read it
-
Information Directed Sampling for Linear Partial Monitoring
Partial monitoring is a rich framework for sequential decision making un...
read it
-
Distributionally Robust Bayesian Optimization
Robustness to distributional shift is one of the key challenges of conte...
read it
-
PACOH: Bayes-Optimal Meta-Learning with PAC-Guarantees
Meta-learning can successfully acquire useful inductive biases from data...
read it
-
Log Barriers for Safe Non-convex Black-box Optimization
We address the problem of minimizing a smooth function f^0(x) over a com...
read it
-
Safe non-smooth black-box optimization with application to policy search
For safety-critical black-box optimization tasks, observations of the co...
read it
-
A Human-in-the-loop Framework to Construct Context-dependent Mathematical Formulations of Fairness
Despite the recent surge of interest in designing and guaranteeing mathe...
read it
-
Safe Exploration for Interactive Machine Learning
In Interactive Machine Learning (IML), we iteratively make decisions and...
read it
-
Robust Model-free Reinforcement Learning with Multi-objective Bayesian Optimization
In reinforcement learning (RL), an autonomous agent learns to perform co...
read it
-
Adaptive Sampling for Stochastic Risk-Averse Learning
We consider the problem of training machine learning models in a risk-av...
read it
-
Convergence Analysis of the Randomized Newton Method with Determinantal Sampling
We analyze the convergence rate of the Randomized Newton Method (RNM) in...
read it
-
No-Regret Learning in Unknown Games with Correlated Payoffs
We consider the problem of learning to play a repeated multi-agent game ...
read it
-
Noise Regularization for Conditional Density Estimation
Modelling statistical relationships beyond the conditional mean is cruci...
read it
-
Structured Variational Inference in Unstable Gaussian Process State Space Models
Gaussian processes are expressive, non-parametric statistical models tha...
read it
-
Mixed-Variable Bayesian Optimization
The optimization of expensive to evaluate, black-box, mixed-variable fun...
read it
-
Safe Contextual Bayesian Optimization for Sustainable Room Temperature PID Control Tuning
We tune one of the most common heating, ventilation, and air conditionin...
read it
-
Stochastic Bandits with Context Distributions
We introduce a novel stochastic contextual bandit model, where at each s...
read it
-
Learning Generative Models across Incomparable Spaces
Generative Adversarial Networks have shown remarkable success in learnin...
read it
-
Online Variance Reduction with Mixtures
Adaptive importance sampling for stochastic optimization is a promising ...
read it
-
Bounding Inefficiency of Equilibria in Continuous Actions Games using Submodularity and Curvature
Games with continuous strategy sets arise in several machine learning pr...
read it
-
AReS and MaRS - Adversarial and MMD-Minimizing Regression for SDEs
Stochastic differential equations are an important modeling class in man...
read it
-
Multi-Player Bandits: The Adversarial Case
We consider a setting where multiple players sequentially choose among a...
read it
-
ODIN: ODE-Informed Regression for Parameter and State Inference in Time-Continuous Dynamical Systems
Parameter inference in ordinary differential equations is an important p...
read it
-
Adaptive Sequence Submodularity
In many machine learning applications, one needs to interactively select...
read it
-
Mathematical Notions vs. Human Perception of Fairness: A Descriptive Approach to Fairness for Machine Learning
Fairness for Machine Learning has received considerable attention, recen...
read it
-
Adaptive and Safe Bayesian Optimization in High Dimensions via One-Dimensional Subspaces
Bayesian optimization is known to be difficult to scale to high dimensio...
read it
-
No-regret Bayesian Optimization with Unknown Hyperparameters
Bayesian optimization (BO) based on Gaussian process models is a powerfu...
read it
-
Information-Directed Exploration for Deep Reinforcement Learning
Efficient exploration remains a major challenge for reinforcement learni...
read it