Search Results for author: Miroslav Dudík

Found 18 papers, 4 papers with code

Convex Analysis at Infinity: An Introduction to Astral Space

no code implementations6 May 2022 Miroslav Dudík, Ziwei Ji, Robert E. Schapire, Matus Telgarsky

Not all convex functions on $\mathbb{R}^n$ have finite minimizers; some can only be minimized by a sequence as it heads to infinity.

Bayesian decision-making under misspecified priors with applications to meta-learning

no code implementations NeurIPS 2021 Max Simchowitz, Christopher Tosh, Akshay Krishnamurthy, Daniel Hsu, Thodoris Lykouris, Miroslav Dudík, Robert E. Schapire

We prove that the expected reward accrued by Thompson sampling (TS) with a misspecified prior differs by at most $\tilde{\mathcal{O}}(H^2 \epsilon)$ from TS with a well specified prior, where $\epsilon$ is the total-variation distance between priors and $H$ is the learning horizon.

Decision Making Meta-Learning +1

Gradient descent follows the regularization path for general losses

no code implementations19 Jun 2020 Ziwei Ji, Miroslav Dudík, Robert E. Schapire, Matus Telgarsky

Recent work across many machine learning disciplines has highlighted that standard descent methods, even without explicit regularization, do not merely minimize the training error, but also exhibit an implicit bias.

Fair Regression: Quantitative Definitions and Reduction-based Algorithms

3 code implementations30 May 2019 Alekh Agarwal, Miroslav Dudík, Zhiwei Steven Wu

Our schemes only require access to standard risk minimization algorithms (such as standard classification or least-squares regression) while providing theoretical guarantees on the optimality and fairness of the obtained solutions.

Fairness

Provably efficient RL with Rich Observations via Latent State Decoding

1 code implementation25 Jan 2019 Simon S. Du, Akshay Krishnamurthy, Nan Jiang, Alekh Agarwal, Miroslav Dudík, John Langford

We study the exploration problem in episodic MDPs with rich observations generated from a small number of latent states.

Q-Learning

Practical Contextual Bandits with Regression Oracles

no code implementations ICML 2018 Dylan J. Foster, Alekh Agarwal, Miroslav Dudík, Haipeng Luo, Robert E. Schapire

A major challenge in contextual bandits is to design general-purpose algorithms that are both practically useful and theoretically well-founded.

General Classification Multi-Armed Bandits

Oracle-Efficient Online Learning and Auction Design

no code implementations5 Nov 2016 Miroslav Dudík, Nika Haghtalab, Haipeng Luo, Robert E. Schapire, Vasilis Syrgkanis, Jennifer Wortman Vaughan

We consider the design of computationally efficient online learning algorithms in an adversarial setting in which the learner has access to an offline optimization oracle.

online learning

Arbitrage-Free Combinatorial Market Making via Integer Programming

no code implementations9 Jun 2016 Christian Kroer, Miroslav Dudík, Sébastien Lahaie, Sivaraman Balakrishnan

We present a new combinatorial market maker that operates arbitrage-free combinatorial prediction markets specified by integer programs.

Off-policy evaluation for slate recommendation

1 code implementation NeurIPS 2017 Adith Swaminathan, Akshay Krishnamurthy, Alekh Agarwal, Miroslav Dudík, John Langford, Damien Jose, Imed Zitouni

This paper studies the evaluation of policies that recommend an ordered set of items (e. g., a ranking) based on some context---a common scenario in web search, ads, and recommendation.

Learning-To-Rank

Budget Constraints in Prediction Markets

no code implementations7 Oct 2015 Nikhil Devanur, Miroslav Dudík, Zhiyi Huang, David M. Pennock

We give a detailed characterization of optimal trades under budget constraints in a prediction market with a cost-function-based automated market maker.

Convex Risk Minimization and Conditional Probability Estimation

no code implementations15 Jun 2015 Matus Telgarsky, Miroslav Dudík, Robert Schapire

This paper proves, in very general settings, that convex risk minimization is a procedure to select a unique conditional probability model determined by the classification problem.

General Classification

Doubly Robust Policy Evaluation and Optimization

no code implementations10 Mar 2015 Miroslav Dudík, Dumitru Erhan, John Langford, Lihong Li

As such, we expect the doubly robust approach to become common practice in policy evaluation and optimization.

Decision Making Multi-Armed Bandits

Contextual Dueling Bandits

no code implementations23 Feb 2015 Miroslav Dudík, Katja Hofmann, Robert E. Schapire, Aleksandrs Slivkins, Masrour Zoghi

The first of these algorithms achieves particularly low regret, even when data is adversarial, although its time and space requirements are linear in the size of the policy space.

online learning

Market Making with Decreasing Utility for Information

no code implementations30 Jul 2014 Miroslav Dudík, Rafael Frongillo, Jennifer Wortman Vaughan

We study information elicitation in cost-function-based combinatorial prediction markets when the market maker's utility for information decreases over time.

Generative and Discriminative Learning with Unknown Labeling Bias

no code implementations NeurIPS 2008 Steven J. Phillips, Miroslav Dudík

For the generative case, we derive an entropy-based weighting that maximizes expected log likelihood under the worst-case true class proportions.

Cannot find the paper you are looking for? You can Submit a new open access paper.