arXiv research

Classifier learns to ignore unreliable feedback from end users.

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

Algorithm minimizes regret in predictive models influenced by their own predictions.

We consider wireless transmission of images in the presence of channel output feedback. From a Shannon theoretic perspective feedback does not improve the asymptotic end-to-end performance, and separate source coding followed by capacity-achieving channel coding, which ignores the feedback signal, achieves the optimal …

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…

Proposes a TS approach for Bayesian optimization with preferential feedback.

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

Feedback improves ESN performance by 30-60% across various tasks.

Algorithm provides online learning guarantees against general comparators in full and bandit feedback.

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

Deep Reinforcement Learning has enabled the control of increasingly complex and high-dimensional problems. However, the need of vast amounts of data before reasonable performance is attained prevents its widespread application. We employ binary corrective feedback as a general and intuitive manner to incorporate human …

Advocates a local feedback approach for RL in unknown systems.

GPT-4 assesses its confidence in answering USMLE questions with and without feedback.

Proposes a method to select fair performance metrics through metric elicitation.

Efficient exploration improves large language model performance with fewer queries.

New techniques improve distributed training with compressed gradients.

New approach detects cyber-attacks in real-time.

A survey is performed of various Multi-Armed Bandit (MAB) strategies in order to examine their performance in circumstances exhibiting non-stationary stochastic reward functions in conjunction with delayed feedback. We run several MAB simulations to simulate an online eCommerce platform for grocery pick up, optimizing …

New study shows feedback doesn't improve MAB performance over erasure channels.

Traditional collaborative filtering (CF) based recommender systems tend to perform poorly when the user-item interactions/ratings are highly scarce. To address this, we propose a learning framework that improves collaborative filtering with a synthetic feedback loop (CF-SFL) to simulate the user feedback. The proposed …

We present online boosting algorithms for multilabel ranking with top-k feedback, where the learner only receives information about the top k items from the ranking it provides. We propose a novel surrogate loss function and unbiased estimator, allowing weak learners to update themselves with limited information. Using…

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…

Online algorithms stabilize in feedback loops of performative prediction.

CAFL breaks feedback loops in recommender systems using causal inference.

ELF improves FM forecasts by efficiently using online feedback.

Hölder-DPO aligns models robustly with noisy human feedback.

DUET optimizes LLM training data mixtures using feedback from unseen tasks.

Interactive weak supervision learns useful heuristics from user feedback.

Dynamic model pruning improves performance on deep neural networks without retraining.

Reinforcement learning with trajectory feedback instead of state-action rewards.

Banker-OMD improves online learning with delayed feedback.

Neural ODEs control graph dynamics with low energy feedback.

Multimodal analysis assesses job interview performance and provides feedback.

In this paper, we utilize information theory to study the fundamental performance limitations of generic feedback systems, where both the controller and the plant may be any causal functions/mappings while the disturbance can be with any distributions. More specifically, we obtain fundamental $\mathcal{L}_p$ bounds on …

We show that deep networks can be trained using Hebbian updates yielding similar performance to ordinary back-propagation on challenging image datasets. To overcome the unrealistic symmetry in connections between layers, implicit in back-propagation, the feedback weights are separate from the feedforward weights. The f…

Framework learns robust control policies from expert demonstrations.

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

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

LoCo-RLHF models diverse human feedback with contextual information.

Simulation-based training (SBT) is gaining popularity as a low-cost and convenient training technique in a vast range of applications. However, for a SBT platform to be fully utilized as an effective training tool, it is essential that feedback on performance is provided automatically in real-time during training. It i…

The paper provides guarantees for feedback control with sensor errors.

New RL algorithm handles delayed feedback with posterior sampling.

DEFINED uses decision feedback ICL to detect symbols with minimal pilot data.

Plug-in method improves performative prediction accuracy.

Current algorithms for deep learning probably cannot run in the brain because they rely on weight transport, where forward-path neurons transmit their synaptic weights to a feedback path, in a way that is likely impossible biologically. An algorithm called feedback alignment achieves deep learning without weight transp…

We study the stochastic multi-armed bandit problem with the graph-based feedback structure introduced by Mannor and Shamir. We analyze the performance of the two most prominent stochastic bandit algorithms, Thompson Sampling and Upper Confidence Bound (UCB), in the graph-based feedback setting. We show that these algor…

RLHF fails when humans only partially observe, leading to inflated or overjustified feedback.