Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

224449673897 · Jun 202019922001200920172026
48 results for Bandit Blackwell Approachability

Transforms offline greedy algorithms to online algorithms for combinatorial problems.

problem Online decision-making in time-varying combinatorial environments.
method General framework using Blackwell approachability and Bandit Blackwell approachability.
result Achieves O(T)O(\sqrt{T}) regret in full information setting and O(T2/3)O(T^{2/3}) regret in bandit setting.

New algorithm achieves both static and dynamic regret optimally against an oblivious adversary for deterministic losses.

problem Achieving optimal static and dynamic regret simultaneously in adversarial bandits.
method Extends impossibility result to deterministic losses, uses negative static regret and Blackwell approachability.
result First algorithm achieving optimal static and dynamic regret simultaneously against an oblivious adversary.

New approach for adaptive conformal inference using Blackwell's theory.

problem Non-exchangeable environments in sequential conformal inference.
method Reinterpretation of ACI as a game, construction of coverage and efficiency objectives, approachability strategy.
result Algorithm achieves strong theoretical guarantees and practical insights.

Blackwell's theorems influence modern AI through information compression and decision making.

problem Information compression and decision making under uncertainty.
method Theorems developed in the 1940s and 1950s, applied to modern AI.
result Blackwell theorems remain relevant and influence modern AI subfields.

Study extends binary omniprediction to multiclass setting with improved sample complexity.

problem Suboptimality bounds for each loss function against infinite comparator family in multiclass prediction.
method Design of a framework for solving Blackwell approachability problems with coupled actions.
result Sample complexity of ε(k+1)\approx \varepsilon^{-(k+1)} for ε\varepsilon-omniprediction in a kk-class problem.

Paper explores rate-preserving reductions between Blackwell approachability and no-regret learning.

problem Tackles rate-preserving reductions between Blackwell approachability and no-regret learning.
method Studies fine-grained reductions and optimal rates of convergence.
result Shows that rate-preserving reductions do not always hold, but provides conditions for when they do.

A game-theoretic approach to multi-criteria ranking from ordinal data.

problem Ranking objects from ordinal data with multiple criteria.
method Generalizing von Neumann winner to multi-criteria setting using Blackwell's approachability.
result The Blackwell winner can be computed as a convex optimization problem and achieves near-optimal sample complexity.

We consider Blackwell approachability, a very powerful and geometric tool in game theory, used for example to design strategies of the uninformed player in repeated games with incomplete information. We extend this theory to "generalized quitting games" , a class of repeated stochastic games in which each player may ha…

2016-09-28abs ↗pdf ↗

Proposes a method to stabilize Black Box Variational Inference using the James-Stein estimator.

problem Stability issues and fine-tuning required in basic Black Box Variational Inference.
method Reframe stochastic gradient ascent as multivariate estimation problem using James-Stein estimator.
result Provides a simpler method with consistent performance in terms of model fit and convergence time.

New method reduces bias in learning from large action spaces using selective importance sampling.

problem Learning from large-scale recommendation systems with bandit feedback and supervised labels.
method Selective Importance Sampling (sIS) and Policy Optimization for eXtreme Models (POXM) algorithm.
result POXM method significantly outperforms existing methods in learning from bandit feedback on XMC tasks.

Fibonacci Ensembles use Fibonacci weights to improve ensemble learning, inspired by natural growth patterns.

problem Improving ensemble learning methods to enhance model performance and interpretability.
method Introduces Fibonacci weights and a recursive ensemble dynamic to reduce variance and enrich representational depth.
result Fibonacci weighting can match or improve upon uniform averaging in ensemble learning experiments.

We wish to compute the gradient of an expectation over a finite or countably infinite sample space having KK \leq \infty categories. When KK is indeed infinite, or finite but very large, the relevant summation is intractable. Accordingly, various stochastic gradient estimators have been proposed. In this paper, we de…

2018-10-10abs ↗pdf ↗

We provide yet another proof of the existence of calibrated forecasters; it has two merits. First, it is valid for an arbitrary finite number of outcomes. Second, it is short and simple and it follows from a direct application of Blackwell's approachability theorem to carefully chosen vector-valued payoff function and …

2009-12-18abs ↗pdf ↗

The paper introduces Robust Correlated Equilibrium for games with time-varying costs and proposes an algorithm to achieve it.

problem Games with time-varying costs and disturbances.
method Proposes Robust Correlated Equilibrium and a decentralized algorithm to learn optimal strategies.
result The algorithm converges to the Robust Correlated Equilibrium, showing no regret for each controller.

Differential privacy is a statistical concept that can be explained through hypothesis testing.

problem Formalizing differential privacy as a statistical concept.
method Using David Blackwell's informativeness theorem, the paper shows differential privacy can be understood through hypothesis testing.
result The definition of ff-differential privacy provides a unified framework for analyzing privacy bounds.

New sampler reduces MCMC complexity for Bayesian variable selection.

problem High-dimensional Bayesian variable selection with high computation complexity.
method Variable-complexity subset weighted-Tempered Gibbs Sampler (wTGS) with Rao-Blackwellized estimator.
result Variances of Rao-Blackwellized estimator are smaller than those of subset wTGS.

New estimator reduces variance in discrete random variables.

problem Estimating gradients for discrete random variables with reduced variance.
method Sampling without replacement and Rao-Blackwellization.
result Our estimator is the most consistent gradient estimator across different entropy settings.

Optimizes predictions by recalibrating online forecasts with minimal error.

problem Tackles the challenge of recalibrating online predictions to be more accurate.
method Uses an imbalanced extension of the Blackwell approachability reduction framework to achieve (ε,ε2)(\varepsilon, \varepsilon^2)-recalibration.
result Achieves (ε,ε2)(\varepsilon, \varepsilon^2)-recalibration for Lipschitz proper losses in Tε3T \approx \varepsilon^{-3} rounds.

The decentralized particle filter (DPF) was proposed recently to increase the level of parallelism of particle filtering. Given a decomposition of the state space into two nested sets of variables, the DPF uses a particle filter to sample the first set and then conditions on this sample to generate a set of samples for…

2012-03-12abs ↗pdf ↗

Calibrated strategies can be obtained by performing strategies that have no internal regret in some auxiliary game. Such strategies can be constructed explicitly with the use of Blackwell's approachability theorem, in an other auxiliary game. We establish the converse: a strategy that approaches a convex BB-set can be…

2010-06-09abs ↗pdf ↗

Partition functions of probability distributions are important quantities for model evaluation and comparisons. We present a new method to compute partition functions of complex and multimodal distributions. Such distributions are often sampled using simulated tempering, which augments the target space with an auxiliar…

2016-03-07abs ↗pdf ↗

New gradient estimators for discrete variables improve model training.

problem Training models with discrete latent variables is challenging due to high gradient variance.
method Introduced novel gradient estimators based on importance sampling and statistical couplings, extending to categorical variables.
result Proposed gradient estimators outperform previous methods in systematic experiments.

Policy optimization on high-dimensional continuous control tasks exhibits its difficulty caused by the large variance of the policy gradient estimators. We present the action subspace dependent gradient (ASDG) estimator which incorporates the Rao-Blackwell theorem (RB) and Control Variates (CV) into a unified framework…

2018-05-09abs ↗pdf ↗

New approach combines semi-supervised learning and bandits for better predictions.

problem Online semi-supervised learning with bandit feedback for applications like clinical trials and ad recommendations.
method Adjusted Graph Convolutional Network (GCN) for contextual bandits, with semi-supervised missing rewards imputation.
result Developed multi-GCN embedded contextual bandit algorithms verified on real-world datasets.

We consider an online decision making setting known as contextual bandit problem, and propose an approach for improving contextual bandit performance by using an adaptive feature extraction (representation learning) based on online clustering. Our approach starts with an off-line pre-training on unlabeled history of co…

2018-02-03abs ↗pdf ↗

New methods for CI testing under model misspecification.

problem Challenges in CI testing with misspecified models.
method Proposes new approximations and upper bounds for testing errors of regression-based CI tests.
result Introduces the Rao-Blackwellized Predictor Test (RBPT) robust against misspecified inductive biases.

New approach reduces unconstrained linear bandits to simpler optimization problems.

problem Unconstrained linear bandits problem.
method Perturbation-based approach combined with comparator-adaptive OLO algorithms.
result First high-probability guarantees for both static and dynamic regret in unconstrained linear bandits.

Balances and eliminates base algorithms in bandits and RL to bound total regret.

problem Model selection in bandits and reinforcement learning with unknown optimal regret.
method Balances and eliminates base algorithms based on candidate regret bounds.
result Total regret bound is the best valid candidate regret bound times a small multiplicative factor.

This paper improves offline contextual bandits using distributional robustness.

problem Improving offline contextual bandits with robustness.
method Extends Distributionally Robust Optimization (DRO) for offline contextual bandits, introducing a convex reformulation of Counterfactual Risk Minimization.
result Automatic calibration of asymptotic confidence intervals for policy optimization.

New framework ensures valid uncertainty estimates for any data stream changes.

problem Challenges of distribution shifts and adversarial actors in real-world data streams.
method Leveraging Blackwell approachability from game theory, the framework guarantees calibrated uncertainties for any compact space.
result Improves calibration and decision-making for energy systems.

New RL method improves on standard discounted RL for operations research.

problem Applying RL to operations research problems, especially with non-zero rewards.
method Near-Blackwell-optimal RL algorithm that assesses average reward per step.
result Proves viability on challenging queuing system problems.