arXiv research

Study shows observing order book can significantly improve online market making performance.

Survey of three geometric frameworks for action-dependent field theories.

New algorithm for online learning with noisy side observations.

Policy gradient methods have enjoyed great success in deep reinforcement learning but suffer from high variance of gradient estimates. The high variance problem is particularly exasperated in problems with long horizons or high-dimensional action spaces. To mitigate this issue, we derive a bias-free action-dependent ba…

We show that J. Lott's equivariant higher analytic torsion for compact group actions depends only on the equivariant Euler characteristic.

Policy gradient methods are a widely used class of model-free reinforcement learning algorithms where a state-dependent baseline is used to reduce gradient estimator variance. Several recent papers extend the baseline to depend on both the state and action and suggest that this significantly reduces variance and improv…

Proposes a neural network for efficient deep hedging strategies.

Efficiently handles contextual bandits with diffusion models.

Efficient algorithms for second-price auctions with action-dependent censoring.

New algorithm tackles multi-agent reinforcement learning with optimal convergence rate.

Policy gradient methods have achieved remarkable successes in solving challenging reinforcement learning problems. However, it still often suffers from the large variance issue on policy gradient estimation, which leads to poor sample efficiency during training. In this work, we propose a control variate method to effe…

In a previous paper we constructed classical spin Chern-Simons for any compact Lie group $G$: a gauge theory whose action depends on the spin structure of the 3-manifold. Here we apply geometric quantization to the classical Hamiltonian theory and investigate the formal properties of the partition function in the Lagra…

New insights into cascade feedback linearization of control systems.

New method learns from either positive or negative feedback alone.

BRPO optimizes batch RL policies to better exploit state-action differences.

User preferences for items can be inferred from either explicit feedback, such as item ratings, or implicit feedback, such as rental histories. Research in collaborative filtering has concentrated on explicit feedback, resulting in the development of accurate and scalable models. However, since explicit feedback is oft…

This paper improves image retrieval accuracy through novel relevance feedback methods.

Recommender systems recommend items more accurately by analyzing users' potential interest on different brands' items. In conjunction with users' rating similarity, the presence of users' implicit feedbacks like clicking items, viewing items specifications, watching videos etc. have been proved to be helpful for learni…

Study evaluates new models using human feedback from another model.

Develops a new model for RLHF accounting for partially observed states and intermediate feedback.

Classifier learns to ignore unreliable feedback from end users.

Paper characterizes minimax regret rates for online ranking with top-k feedback.

Study on sample complexity for pure exploration in feedback graph settings.

Let G be a group and let M be a CAT(0) proper metric space (e.g. a simply connected complete Riemannian manifold of non-positive sectional curvature or a locally finite tree). Isometric actions of G on M are (by definition) points in the space R := Hom(G, Isom(M)) with the compact open topology. Sample theorems: 1. The…

One-bit feedback suffices for a bandit problem's optimal strategy.

Advocates a local feedback approach for RL in unknown systems.

A method corrects feedback shift in predicting conversion rates with delayed feedback.

Study how communication and feedback graphs affect learning outcomes.

New method uses correlated auxiliary feedback to reduce regret in parameterized bandits.

Test for linearizing 2-input systems with 2D feedback.

Linear recurrent networks explain reinforcement learning performance in partially observable settings.

The problem of feedback equivalence for control systems is considered. An algebra of differential invariants and criteria for the feedback equivalence for regular control systems are found.

Reduces user feedback needed for accurate recommender systems.

We present a study on reinforcement learning (RL) from human bandit feedback for sequence-to-sequence learning, exemplified by the task of bandit neural machine translation (NMT). We investigate the reliability of human bandit feedback, and analyze the influence of reliability on the learnability of a reward estimator,…

New algorithm for recommending best arms with aggregated feedback.

Study of reinforcement learning with additional feedback observations.

CausalRM models rewards from user feedback, overcoming noise and bias.

Paper tackles noisy bandit feedback for multiclass classification.

We propose a generalization of the best arm identification problem in stochastic multi-armed bandits (MAB) to the setting where every pull of an arm is associated with delayed feedback. The delay in feedback increases the effective sample complexity of standard algorithms, but can be offset if we have access to partial…

Easy conditions found for simplifying complex systems.

Active learning framework for optimizing human preferences in reinforcement learning.

Paper studies CLO with partial feedback, improving decision-making in uncertain contexts.

We use online convex optimization (OCO) for setpoint tracking with uncertain, flexible loads. We consider full feedback from the loads, bandit feedback, and two intermediate types of feedback: partial bandit where a subset of the loads are individually observed and the rest are observed in aggregate, and Bernoulli feed…

CAFL breaks feedback loops in recommender systems using causal inference.

We consider combinatorial online learning with subset choices when only relative feedback information from subsets is available, instead of bandit or semi-bandit feedback which is absolute. Specifically, we study two regret minimisation problems over subsets of a finite ground set $[n]$, with subset-wise relative prefe…

Unified framework for expert selection with bandit and lower-bound feedback.

GAIF enhances online multiple testing with feedback, improving statistical power.

New algorithms handle online prediction with bandit and delayed feedback, improving regret bounds.