arXiv research

Thompson Sampling tackles noisy context in stochastic bandits.

New algorithm reduces regret in noisy context bandits.

This study uses ICL to efficiently generate robust confidence intervals for noisy regression tasks.

Transformers can learn noisy linear systems with depth and IID data.

CbMLC improves multi-label classification with noisy labels.

Paper shows how noisy data can improve robust decision-making.

Paper studies zero-sum games with noisy observations and identifies equilibrium conditions.

This research tackles unsupervised topic extraction in noisy social media data.

Compressed LLM embeddings improve noisy regression tasks without overfitting.

Learning from unlabeled and noisy data is one of the grand challenges of machine learning. As such, it has seen a flurry of research with new ideas proposed continuously. In this work, we revisit a classical idea: Stein's Unbiased Risk Estimator (SURE). We show that, in the context of image recovery, SURE and its gener…

Noisy labels often occur in vision datasets, especially when they are obtained from crowdsourcing or Web scraping. We propose a new regularization method, which enables learning robust classifiers in presence of noisy data. To achieve this goal, we propose a new adversarial regularization scheme based on the Wasserstei…

New algorithm learns optimal decisions from imperfectly observed contexts.

Single Molecule Real-Time (SMRT) sequencing is a recent advancement of Next Gen technology developed by Pacific Bio (PacBio). It comes with an explosion of long and noisy reads demanding cutting edge research to get most out of it. To deal with the high error probability of SMRT data, a novel contextual Locality Sensit…

Label aggregation makes learning robust to noisy labels.

We analyze the $K$-armed bandit problem where the reward for each arm is a noisy realization based on an observed context under mild nonparametric assumptions. We attain tight results for top-arm identification and a sublinear regret of $\widetilde{O}\Big(T^{\frac{1+D}{2+D}}\Big)$, where $D$ is the context dimension, f…

SDA method reduces memory and time for assimilating noisy geophysical data.

Entity linking is the task of mapping potentially ambiguous terms in text to their constituent entities in a knowledge base like Wikipedia. This is useful for organizing content, extracting structured data from textual documents, and in machine learning relevance applications like semantic search, knowledge graph const…

Low dimensional embeddings that capture the main variations of interest in collections of data are important for many applications. One way to construct these embeddings is to acquire estimates of similarity from the crowd. However, similarity is a multi-dimensional concept that varies from individual to individual. Ex…

Although the standard formulations of prediction problems involve fully-observed and noiseless data drawn in an i.i.d. manner, many applications involve noisy and/or missing data, possibly involving dependence, as well. We study these issues in the context of high-dimensional sparse linear regression, and propose novel…

The paper explores fair machine learning policies for balancing competing objectives in noisy data.

New oracles improve stochastic optimization with noisy or biased measurements.

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

Attention-only transformers learn from context via two stages of inference.

Multi-head attention outperforms single-head in in-context linear regression tasks.

Transformers trained on random classification tasks generalize well and can overfit without error.

Transformers enable in-context learning with guarantees for a wide range of tasks.

Paper tackles federated linear bandit learning with AirComp for noisy channels.

Study improves estimation of functions from noisy data using convex penalties.

Novel loss functions improve decision tree learning from noisy data.

Method separates target signal properties from noisy mixtures.

Framework for Bayesian inference using GP emulated MH sampler for noisy likelihoods.

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

CTEF fits ellipsoids to noisy data in any dimension.

It has been observed in a variety of contexts that gradient descent methods have great success in solving low-rank matrix factorization problems, despite the relevant problem formulation being non-convex. We tackle a particular instance of this scenario, where we seek the $d$-dimensional subspace spanned by a streaming…

Approximate Message Passing (AMP) has been shown to be a superior method for inference problems, such as the recovery of signals from sets of noisy, lower-dimensionality measurements, both in terms of reconstruction accuracy and in computational efficiency. However, AMP suffers from serious convergence issues in contex…

Transformers can adaptively select and perform various machine learning tasks in context.

Study improves resilience against adversarial clean-label attacks in real and noisy settings.

LangDA improves domain adaptation for semantic segmentation by learning context-aware scene descriptions.

Attention temperature improves robustness of ICL in high-dimensional settings.

Model detects patterns in noisy binary data, explaining neuron activity in terms of cell assemblies.

Market-GAN adds context control to financial market data generation.

Algorithm minimizes regret in dueling bandits with contextualized utilities.

This paper recovers smooth functions from noisy modulo samples using a three-stage strategy.

A new method learns Hamiltonian functions from noisy data.

This letter proposes a low-computational Bayesian algorithm for noisy sparse recovery in the context of one bit compressed sensing with sensing matrix perturbation. The proposed algorithm which is called BHT-MLE comprises a sparse support detector and an amplitude estimator. The support detector utilizes Bayesian hypot…

High-dimensional time series prediction is needed in applications as diverse as demand forecasting and climatology. Often, such applications require methods that are both highly scalable, and deal with noisy data in terms of corruptions or missing values. Classical time series methods usually fall short of handling bot…

Gradient-descent-based algorithms and their stochastic versions have widespread applications in machine learning and statistical inference. In this work we perform an analytic study of the performances of one of them, the Langevin algorithm, in the context of noisy high-dimensional inference. We employ the Langevin alg…

We consider the problem of learning the level set for which a noisy black-box function exceeds a given threshold. To efficiently reconstruct the level set, we investigate Gaussian process (GP) metamodels. Our focus is on strongly stochastic samplers, in particular with heavy-tailed simulation noise and low signal-to-no…