arXiv research

Online learning with one-sided feedback aims to maximize accuracy while ensuring fairness.

Algorithm minimizes regret in multi-criteria bandits with constraints.

Benchmarking deep time series models for equity portfolios

Multi-criteria recommender systems have been increasingly valuable for helping consumers identify the most relevant items based on different dimensions of user experiences. However, previously proposed multi-criteria models did not take into account latent embeddings generated from user reviews, which capture latent se…

A new method for multi-criteria recommender systems using graph attention networks.

Develops scenario theory for multi-criteria decision making.

Framework selects real estate redevelopment uses by integrating value, risk, complexity, and irreversibility.

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

We solve the multi-criteria benchmarking problem by formalizing it as a social choice problem and identifying conditions for meaningful rankings.

New method optimizes multiple objectives in A/B testing for AI and clinical trials.

Proposes a new framework for predicting stock market movements using sparse neural architectures.

Efficient algorithms for online learning with changing action sets, achieving no-approximate-regret guarantees.

Paper solves no-swap regret minimization for combinatorial bandits with polylogarithmic dependence on N.

New method finds optimal hyperparameters for multiple tasks and criteria.

No-regret learning with strategic experts, incentivized.

No-regret optimization for time-varying functions using uncertainty injection.

The notion of \emph{policy regret} in online learning is a well defined? performance measure for the common scenario of adaptive adversaries, which more traditional quantities such as external regret do not take into account. We revisit the notion of policy regret and first show that there are online learning settings …

New insights link no-regret learning to online conformal prediction in adversarial settings.

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

Proposes a new stability measure for model fitting on similar feature data sets.

Paper proposes OPF policy for fair resource allocation with sublinear regret.

We introduce CSE for MLSF games and devise online learning algorithms for achieving no-external Stackelberg-regret.

This paper tackles no-regret learning for fair multi-agent social welfare optimization.

This work forecasts electricity prices using Bayesian regime detection and conditional neural processes.

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 $B$-set can be…

No-regret learning fails to converge to Nash equilibria in mixed strategies.

Paper analyzes GP-EI for Bayesian optimization with no regret and provides guidance on choosing incumbents.

The paper analyzes the sliding regret of stochastic bandit algorithms.

Paper establishes no-regret property for practical EGO optimization.

New algorithms achieve no-regret learning even with adversarial transitions and losses.

New framework uses PDE for no-regret generative modeling.

No communication allows optimal instance-dependent regret guarantees in multi-player bandits.

New research shows no-regret learning is impossible in Markov games under certain assumptions.

Paper proposes no-regret algorithms for private GP bandit optimization.

The paper tackles robust policy learning from multiple data sources.

New strategy achieves optimal regret without communication or collisions in multi-player bandit.

There are two variants of the classical multi-armed bandit (MAB) problem that have received considerable attention from machine learning researchers in recent years: contextual bandits and simple regret minimization. Contextual bandits are a sub-class of MABs where, at every time step, the learner has access to side in…

A new mechanism reduces expert belief regret in online forecasting.

We consider the classical stochastic multi-armed bandit but where, from time to time and roughly with frequency $ε$, an extra observation is gathered by the agent for free. We prove that, no matter how small $ε$ is the agent can ensure a regret uniformly bounded in time. More precisely, we construct an algorithm with a…

Counterfactual Regret Minimization (CFR) has found success in settings like poker which have both terminal states and perfect recall. We seek to understand how to relax these requirements. As a first step, we introduce a simple algorithm, local no-regret learning (LONR), which uses a Q-learning-like update rule to allo…

We consider the problem of identifying patterns in a data set that exhibit anomalous behavior, often referred to as anomaly detection. In most anomaly detection algorithms, the dissimilarity between data samples is calculated by a single criterion, such as Euclidean distance. However, in many cases there may not exist …

MOSAIC selects few informative exemplars from high-dimensional data with non-linear structures.

Framework for games with uncertain parameters, ensuring no player can improve by changing strategy.

Kernel-based function approximation improves reinforcement learning performance.

Optimistic Thompson Sampling reduces regret in unknown multi-player games.

LIBO optimizes repeated bandit tasks without prior knowledge or regret.

Random forests are among the most popular classification and regression methods used in industrial applications. To be effective, the parameters of random forests must be carefully tuned. This is usually done by choosing values that minimize the prediction error on a held out dataset. We argue that error reduction is o…

New algorithm for multi-player bandits with collision-dependent rewards.