arXiv research

Enhances activity recognition in wearable computing with context awareness and uncertainty quantification.

Optimal algorithm for contextual bandits with unknown context distributions.

A federated learning algorithm tackles unknown contexts in multi-arm bandits.

Develops a robust learning method for unknown context distributions.

Consider a nonparametric contextual multi-arm bandit problem where each arm $a \in [K]$ is associated to a nonparametric reward function $f_a: [0,1] \to \mathbb{R}$ mapping from contexts to the expected reward. Suppose that there is a large set of arms, yet there is a simple but unknown structure amongst the arm reward…

Paper solves stochastic contextual linear bandits using linear bandit algorithms.

New Thompson Sampling for partially observed context bandits reduces regret logarithmically with time.

In real-world scenarios, different features have different acquisition costs at test-time which necessitates cost-aware methods to optimize the cost and performance trade-off. This paper introduces a novel and scalable approach for cost-aware feature acquisition at test-time. The method incrementally asks for features …

Algorithm identifies best arm in piecewise stationary linear bandits with minimal samples.

New method reduces regret in nonparametric bandits with unknown covariate shifts.

Optimal pricing strategy for unknown valuation models with noisy feedback.

Thompson Sampling tackles noisy context in stochastic bandits.

ICON-OCnet solves optimal execution problems with neural networks and few examples.

Unified approach to fair online learning with stochastic contexts.

For many important problems the quantity of interest is an unknown function of the parameters, which is a random vector with known statistics. Since the dependence of the output on this random vector is unknown, the challenge is to identify its statistics, using the minimum number of function evaluations. This problem …

We study contextual bandits with budget and time constraints, referred to as constrained contextual bandits.The time and budget constraints significantly complicate the exploration and exploitation tradeoff because they introduce complex coupling among contexts over time.Such coupling effects make it difficult to obtai…

Minimax PAC bounds for learning in exogenous contextual MDPs

Generalization and adaptation of learned skills to novel situations is a core requirement for intelligent autonomous robots. Although contextual reinforcement learning provides a principled framework for learning and generalization of behaviors across related tasks, it generally relies on uninformed sampling of environ…

A new algorithm optimizes unknown functions with noisy data and unmatched features.

New algorithm reduces online learning error for unknown feature distributions.

New algorithm for context bandits with continuous actions.

Paper establishes MLE consistency for market microstructure models.

New approach for learning with unknown utilities without explicit specification.

Despite significant effort in understanding complex systems (CS), we lack a theory for modeling, inference, analysis and efficient control of time-varying complex networks (TVCNs) in uncertain environments. From brain activity dynamics to microbiome, and even chromatin interactions within the genome architecture, many …

Greedy policies perform poorly in imperfectly observed contextual bandits.

Paper tackles blind polynomial regression for unknown inputs.

CAZSL learns to generalize physical interactions from context.

Transformer learns context and regularization for ICL in inverse problems.

Transformer learns to infer partial MDPs for efficient in-context adaptation and exploration.

Develops inverse extended Kalman filter for predicting adversarial steps.

We explore the sequential decision making problem where the goal is to estimate uniformly well a number of linear models, given a shared budget of random contexts independently sampled from a known distribution. The decision maker must query one of the linear models for each incoming context, and receives an observatio…

The problem of optimizing unknown costly-to-evaluate functions has been studied for a long time in the context of Bayesian Optimization. Algorithms in this field aim to find the optimizer of the function by asking only a few function evaluations at locations carefully selected based on a posterior model. In this paper,…

EDRBO optimizes Bayesian optimization with continuous contexts using ensemble models and robust methods.

The paper explores how to find relevant vertices in one graph using another graph's attributes and structure.

The classical approach to linear system identification is given by parametric Prediction Error Methods (PEM). In this context, model complexity is often unknown so that a model order selection step is needed to suitably trade-off bias and variance. Recently, a different approach to linear system identification has been…

Motivation: Cell-biological processes are regulated through a complex network of interactions between genes and their products. The processes, their activating conditions, and the associated transcriptional responses are often unknown. Organism-wide modeling of network activation can reveal unique and shared mechanisms…

Efficient RL for linear MDPs with unknown transitions.

In the context of stochastic continuum-armed bandits, we present an algorithm that adapts to the unknown smoothness of the objective function. We exhibit and compute a polynomial cost of adaptation to the H{ö}lder regularity for regret minimization. To do this, we first reconsider the recent lower bound of Locatelli an…

We propose a new algorithm to learn a dictionary for reconstructing and sparsely encoding signals from measurements without phase. Specifically, we consider the task of estimating a two-dimensional image from squared-magnitude measurements of a complex-valued linear transformation of the original image. Several recent …

Algorithm identifies Pareto front using multiple context directions and reuses exploration samples.

In risk management, tail risks are of crucial importance. The assessment of risks should be carried out in accordance with the regulatory authority's requirement at high quantiles. In general, the underlying distribution function is unknown, the database is sparse, and therefore special tail models are used. Very often…

A novel bandit problem with context-dependent rewards and blocking.

Improves machine learning models by incorporating physical laws into feature maps.

The paper models and predicts co-occurrence counts using Gamma regression.

A new method for density estimation using nearest neighbor Dirichlet mixtures.

New algorithm reduces regret for linear bandits with unknown noise variance.

A new algorithm tackles graph-based contextual bandits with efficient regret bounds.

We consider the problem of learning overcomplete dictionaries in the context of sparse coding, where each sample selects a sparse subset of dictionary elements. Our main result is a strategy to approximately recover the unknown dictionary using an efficient algorithm. Our algorithm is a clustering-style procedure, wher…