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

326395126 · Jun 202019922001200920172026
48 results for batched feedback

New algorithms tackle adversarial combinatorial bandits with switching costs.

problem Adversarial combinatorial bandits with switching costs.
method Design algorithms operating in batches to restrict switches, proving lower bounds and achieving upper bounds on regret.
result Achieved upper bounds on regret for both bandit and semi-bandit feedback settings.

We present two algorithms for Bayesian optimization in the batch feedback setting, based on Gaussian process upper confidence bound and Thompson sampling approaches, along with frequentist regret guarantees and numerical results.

2019-11-04abs ↗pdf ↗

BaNk-UCB tackles batched nonparametric bandits with k-NN regression and UCB.

problem Sequential decision-making with limited online feedback in domains like medicine and marketing.
method Combines k-NN regression with UCB principle for fully nonparametric, adaptive, and simple implementation.
result Near-optimal regret guarantees under Lipschitz smoothness and margin assumptions, with minimax-optimal rates.

Proposes a new semi-parametric framework for batched bandits with covariates.

problem Sequential decision-making with batched feedback and contextual information.
method Batched single-Index Dynamic binning and Successive arm elimination (BIDS) using single-index regression.
result Achieves minimax-optimal rates for nonparametric batched bandits.

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…

2018-03-29abs ↗pdf ↗

Meta-algorithm for efficient reinforcement learning from human preferences.

problem Learning from human preference comparisons in Markov decision processes.
method Randomized exploration and experimental design for batch comparison queries.
result Meta-algorithm achieves both regret and last-iterate guarantees with minimal preference queries.

New method for identifying best arm in batched multi-armed bandit problems.

problem Identifying the best arm in multi-armed bandit problems where arms are sampled in batches.
method General linear programming framework for best arm identification in batched multi-armed bandit problems.
result Demonstrated good performance in numerical studies compared to UCB-type or Thompson sampling methods.

New algorithm tackles batched stochastic linear bandits with 1-bit communication constraints.

problem Stochastic linear bandits with 1-bit communication constraints.
method Phased-elimination algorithms based on G-optimal designs and 1-bit mean estimation.
result Achieves near-optimal regret bounds for broad scaling regimes.

The paper refines and extends batched kernelized bandits, improving regret bounds and introducing a robust setting.

problem Optimizing black-box functions with noisy batches in Reproducing Kernel Hilbert Space.
method Refined and extended existing regret bounds, including adaptive batch sizes and robust optimization.
result Improved regret bounds for batched kernelized bandits, showing optimal number of batches and adaptive batch sizes.

What is the most statistically efficient way to do off-policy evaluation and optimization with batch data from bandit feedback? For log data generated by contextual bandit algorithms, we consider offline estimators for the expected reward from a counterfactual policy. Our estimators are shown to have lowest variance in…

2018-09-10abs ↗pdf ↗

Study model selection in batch policy optimization with three error sources.

problem Learn a policy competitive with the best model class in batch policy optimization.
method Formalized in contextual bandit setting with linear model classes, addressing approximation error, statistical complexity, and dataset shift.
result No algorithm can optimally trade-off all three error sources, but relaxing any one enables near-oracle inequalities for the others.

Develops a flexible batched experimentation framework for limited adaptivity.

problem Challenges of continual reallocation in bandit algorithms with delayed feedback.
method Computational framework leveraging Gaussian sequential experiment and dynamic programming.
result Improves statistical power over standard methods, even compared to Bayesian bandit algorithms.

Generative models enhance BO for large batch optimization.

problem Efficiently sampling solutions in high-dimensional, combinatorial design spaces.
method Train generative models to sample solutions proportional to expected utility.
result Generative models can approximate optimal target distributions under certain conditions.

FAWMF adapts weights for implicit feedback recommendation efficiently.

problem Challenges in treating unobserved data as negative in implicit feedback recommendation.
method FAWMF uses a variational auto-encoder with a parameterized neural network to adaptively assign personalized data confidence weights, and fBGD for efficient learning.
result FAWMF and fBGD outperform existing methods in real-world datasets.

We develop a learning principle and an efficient algorithm for batch learning from logged bandit feedback. This learning setting is ubiquitous in online systems (e.g., ad placement, web search, recommendation), where an algorithm makes a prediction (e.g., ad ranking) for a given input (e.g., query) and observes bandit …

2015-02-09abs ↗pdf ↗

We study online learning when partial feedback information is provided following every action of the learning process, and the learner incurs switching costs for changing his actions. In this setting, the feedback information system can be represented by a graph, and previous works studied the expected regret of the le…

2018-10-23abs ↗pdf ↗

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.

Study online learning with delays and capacity constraints, achieving optimal regret bounds.

problem Online learning with delays and capacity constraints.
method Novel scheduling and preemptive techniques, matching upper and lower bounds.
result Achieves optimal regret bounds across all capacity levels.

Paper introduces MoTEF for faster decentralized optimization with compressed communication.

problem Efficiency bottleneck in decentralized machine learning applications.
method Integrates communication compression with Momentum Tracking and Error Feedback.
result Significantly outperforms existing methods under arbitrary data heterogeneity.

New RLHF algorithm identifies optimal policies from human feedback without explicit reward inference.

problem Training large language models with human feedback without reward inference.
method Model-free RLHF algorithm BSAD\mathsf{BSAD} that identifies optimal policies directly from human preference.
result Provable, instance-dependent sample complexity ildeO(cMSA3H3Mlog1δ) ilde{\mathcal{O}}(c_{\mathcal{M}}SA^3H^3M\log\frac{1}δ).

Online L2D algorithm for multiclass classification with varying experts.

problem Handling streaming data, changing expert availability, and shifting expert distribution.
method First online L2D algorithm with O((n+ne)T2/3)O((n+n_e)T^{2/3}) and O((n+ne)T)O((n+n_e)\sqrt{T}) regret guarantees.
result Effective extension of standard L2D to settings with varying expert availability and reliability.

New algorithm achieves near-optimal performance in dueling bandit problem.

problem Optimizing decision-making in dueling bandit problems with limited adaptive rounds.
method Developed a batched algorithm that matches the asymptotic regret bounds of sequential algorithms under the Condorcet condition.
result Asymptotic regret of O(K2log2(K))+O(Klog(T))O(K^2\log^2(K)) + O(K\log(T)) in O(log(T))O(\log(T)) rounds.

We propose to incorporate adversarial dropout in generative multi-adversarial networks, by omitting or dropping out, the feedback of each discriminator in the framework with some probability at the end of each batch. Our approach forces the single generator not to constrain its output to satisfy a single discriminator,…

2018-07-30abs ↗pdf ↗

Bayesian sOED uses PG reinforcement learning for efficient experiment design.

problem Optimizing sequential experiments for nonlinear models with limited data.
method Formulated as POMDP, solved via PG methods with neural network parameterization.
result Demonstrated advantages over batch and greedy designs in contaminant source inversion.

Optimistic PPO variant solves linear MDPs with improved regret bound.

problem Understanding theoretical limits of PPO in linear MDPs.
method Proposes an optimistic variant of PPO for episodic adversarial linear MDPs with full-information feedback.
result Establishes a ildeO(d3/4H2K3/4) ilde{\mathcal{O}}(d^{3/4}H^2K^{3/4}) regret bound.

The paper tackles performative policy learning with strategic agents, improving scalability and generalizability.

problem Strategic agents adjust their features in response to a released policy, causing endogenous distribution shifts.
method Relaxing parametric assumptions, the paper uncovers a low-dimensional structure in distribution shifts and proposes a gradient-based policy optimization algorithm.
result The proposed algorithm achieves high sample efficiency and provides theoretical guarantees for convergence.

Two algorithms for linear contextual bandits with rare updates achieve optimal regret and efficiency.

problem Linear contextual bandits with infrequent parameter updates.
method Two practical algorithms with O(loglogT)O(\log\log T) updates, BLCE-G and BLCE.
result Minimax-optimal regret with low computational complexity.

New insights into cascade feedback linearization of control systems.

problem Obtaining a cascade feedback linearization for invariant control systems.
method Introducing truncated versions of operators from the calculus of variations to prove new theorems.
result Established new geometry and foundational theorems for future work.

Bayesian model for energy consumption helps electric vehicles navigate efficiently.

problem Limited battery capacity in electric vehicles makes energy efficient navigation challenging.
method Developed an online learning framework using Bayesian models and exploration strategies like Thompson Sampling.
result Established rigorous regret bounds for Thompson Sampling in both single-agent and multi-agent settings.

The paper tackles carousel personalization in music streaming apps using contextual bandits.

problem Selecting relevant items to display in carousels for personalized content recommendation.
method Modeling carousel personalization as a contextual multi-armed bandit problem with multiple plays, cascade-based updates and delayed batch feedback.
result Empirically shows the effectiveness of the framework in capturing characteristics of real-world carousels.

New method learns from either positive or negative feedback alone.

problem Limited applicability of existing preference optimization methods in scenarios with only unpaired feedback.
method Decouples learning from positive and negative feedback, using expectation-maximization (EM) to optimize probability of positive outcomes and explicitly incorporate negative examples.
result Stable learning from negative feedback alone demonstrated.