arXiv research

FAWMF adapts weights for implicit feedback recommendation efficiently.

Quantized Adam reduces communication cost in deep learning training.

Adaptive MAB algorithms handle composite, anonymous feedback without reward interval knowledge.

ELF improves FM forecasts by efficiently using online feedback.

Unified framework for analyzing online convex optimization across various settings.

The article is devoted to investigating the application of hedging strategies to online expert weight allocation under delayed feedback. As the main result, we develop the General Hedging algorithm $\mathcal{G}$ based on the exponential reweighing of experts' losses. We build the artificial probabilistic framework and …

Paper fine-tunes LLMs using user edits, unifying preference, supervision, and reward feedback.

Study the tradeoffs of bandit feedback in multiclass classification.

Algorithm improves query recommendations with immediate user feedback.

Bayesian model identifies three types of travelers adapting to feedback.

ATLAS uses LLMs to adaptively trade by optimizing prompts and coordinating agents.

Interactive Machine Learning is concerned with creating systems that operate in environments alongside humans to achieve a task. A typical use is to extend or amplify the capabilities of a human in cognitive or physical ways, requiring the machine to adapt to the users' intentions and preferences. Often, this takes the…

Paper measures cognitive bias in positive feedback trading using diffusion process estimates.

New algorithm improves cache management with delayed feedback and decaying costs.

Adaptive reward models capture individual preferences from human feedback.

Estimates mode from partial feedback, improving AI learning pipelines.

New algorithm for recommending best arms with aggregated feedback.

Study on collaborative vs. non-collaborative online and bandit convex optimization.

Delaytron learns multi-class classifiers with delayed feedbacks, achieving efficient regret bounds.

Study selective classification with limited feedback in online learning.

Paper tackles domain adaptation for contextual bandits with sub-linear regret.

New oracle uses uncertainty for active classification with noisy feedback.

New algorithm reduces dynamic regret in time-varying movement costs.

New algorithm reduces regret in delayed feedback generalised linear bandits.

The paper tackles efficient change point detection with limited samples.

New algorithm handles delayed feedback robustly, reducing regret without knowing delay bounds.

Quantum-enhanced metrology aims to estimate an unknown parameter such that the precision scales better than the shot-noise bound. Single-shot adaptive quantum-enhanced metrology (AQEM) is a promising approach that uses feedback to tweak the quantum process according to previous measurement outcomes. Techniques and form…

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…

Proposes RPG-RT for red-teaming T2I models without internal access.

A new method for online prediction uncertainty quantification in non-exchangeable panel data.

Learning from human feedback is a viable alternative to control design that does not require modelling or control expertise. Particularly, learning from corrective advice garners advantages over evaluative feedback as it is a more intuitive and scalable format. The current state-of-the-art in this field, COACH, has pro…

Semi-supervised method enhances recommendation from sparse data.

Bandit structured prediction describes a stochastic optimization framework where learning is performed from partial feedback. This feedback is received in the form of a task loss evaluation to a predicted output structure, without having access to gold standard structures. We advance this framework by lifting linear ba…

We derive upper and lower bounds for the policy regret of $T$-round online learning problems with graph-structured feedback, where the adversary is nonoblivious but assumed to have a bounded memory. We obtain upper bounds of $\widetilde O(T^{2/3})$ and $\widetilde O(T^{3/4})$ for strongly-observable and weakly-observab…

DART optimizes subset selection in non-linear bandit problems.

New method clusters items with bandit feedback without parametric assumptions.

Convolutional neural networks (CNNs) are commonly used for image classification tasks, raising the challenge of their application on data flows. During their training, adaptation is often performed by tuning the learning rate. Usual learning rate strategies are time-based i.e. monotonously decreasing. In this paper, we…

Adapts Exp3 to adversarial bandits with delays and data.

Adaptive sampler improves recommendation for implicit feedback data.

DOPL learns from preference feedback to solve RMAB problems.

Optimistic covariance-adaptive algorithms improve combinatorial semi-bandits regret.

A new algorithm tackles delayed combinatorial semi-bandit with causal relations.

We study the power of different types of adaptive (nonoblivious) adversaries in the setting of prediction with expert advice, under both full-information and bandit feedback. We measure the player's performance using a new notion of regret, also known as policy regret, which better captures the adversary's adaptiveness…

We introduce a new class of reinforcement learning methods referred to as {\em episodic multi-armed bandits} (eMAB). In eMAB the learner proceeds in {\em episodes}, each composed of several {\em steps}, in which it chooses an action and observes a feedback signal. Moreover, in each step, it can take a special action, c…

Work shows hallucination detection by LLMs is impossible without expert feedback.

Item recommendation is the task of predicting a personalized ranking on a set of items (e.g. websites, movies, products). In this paper, we investigate the most common scenario with implicit feedback (e.g. clicks, purchases). There are many methods for item recommendation from implicit feedback like matrix factorizatio…

Paper analyzes nonconvex bandit problems with improved adaptive methods.

Adaptive ML learns complex time-varying systems without new data.