arXiv research

Latent FxLMS accelerates ANC by adapting along low-dimensional filter weights.

New method for learning indirectly through control variables.

GRIP2 improves deep learning feature selection robustness in correlated and noisy data.

New active learning methods for Gaussian process improve predictive modeling of composite fuselage.

Brain-computer interfaces (BCIs) have enabled prosthetic device control by decoding motor movements from neural activities. Neural signals recorded from cortex exhibit nonstationary property due to abrupt noises and neuroplastic changes in brain activities during motor control. Current state-of-the-art neural signal de…

New method disentangles perceptual uncertainty and behavioral costs in partially observable systems.

Noise Sensitivity Exponent controls statistical-computational gaps in learning.

Automated quality control for seismic data reduces human labor and time.

We propose an algorithm to actively estimate the parameters of a linear dynamical system. Given complete control over the system's input, our algorithm adaptively chooses the inputs to accelerate estimation. We show a finite time bound quantifying the estimation rate our algorithm attains and prove matching upper and l…

Derives time-averaged active inference from control principles.

New method controls false detections in brain activity localization.

Study shows sample noise impacts active learning performance.

An increasing body of evidence suggests that the trial-to-trial variability of spiking activity in the brain is not mere noise, but rather the reflection of a sampling-based encoding scheme for probabilistic computing. Since the precise statistical properties of neural activity are important in this context, many model…

Volatility estimation based on high-frequency data is key to accurately measure and control the risk of financial assets. A Lévy process with infinite jump activity and microstructure noise is considered one of the simplest, yet accurate enough, models for financial data at high-frequency. Utilizing this model, we prop…

This work designs an active world model learning system with progress-based curiosity.

We describe a framework for designing efficient active learning algorithms that are tolerant to random classification noise and are differentially-private. The framework is based on active learning algorithms that are statistical in the sense that they rely on estimates of expectations of functions of filtered random e…

This work establishes distribution-free upper and lower bounds on the minimax label complexity of active learning with general hypothesis classes, under various noise models. The results reveal a number of surprising facts. In particular, under the noise model of Tsybakov (2004), the minimax label complexity of active …

Efficient algorithm for halfspaces with specific noise conditions.

SAP corrects model for label noise by identifying and removing noisy samples.

In active learning, the user sequentially chooses values for feature $X$ and an oracle returns the corresponding label $Y$. In this paper, we consider the effect of feature noise in active learning, which could arise either because $X$ itself is being measured, or it is corrupted in transmission to the oracle, or the o…

Common nonlinear activation functions used in neural networks can cause training difficulties due to the saturation behavior of the activation function, which may hide dependencies that are not visible to vanilla-SGD (using first order gradients only). Gating mechanisms that use softly saturating activation functions t…

Study efficient active learning for halfspaces with Tsybakov noise using non-convex optimization.

This work frames active inference through control as inference, offering robust control algorithms.

Paper tackles online control of linear systems with unbounded noise.

We study the theoretical advantages of active learning over passive learning. Specifically, we prove that, in noise-free classifier learning for VC classes, any passive learning algorithm can be transformed into an active learning algorithm with asymptotically strictly superior label complexity for all nontrivial targe…

Proposes an offline active learning method for graphs.

Complexity measures for neural nets with general activations using path-based norms.

Decoupled PFNs improve sequential decision-making by separating epistemic and aleatoric uncertainties.

This work addresses various open questions in the theory of active learning for nonparametric classification. Our contributions are both statistical and algorithmic: -We establish new minimax-rates for active learning under common \textit{noise conditions}. These rates display interesting transitions -- due to the inte…

Performing controlled experiments on noisy data is essential in understanding deep learning across noise levels. Due to the lack of suitable datasets, previous research has only examined deep learning on controlled synthetic label noise, and real-world label noise has never been studied in a controlled setting. This pa…

We show LLMs can be locally linear, enabling better control of activations.

Paper studies central bank's strategy to control systemic risk in interbank system.

We introduce the active exploration problem in Markov decision processes (MDPs). Each state of the MDP is characterized by a random value and the learner should gather samples to estimate the mean value of each state as accurately as possible. Similarly to active exploration in multi-armed bandit (MAB), states may have…

We present a simple noise-robust margin-based active learning algorithm to find homogeneous (passing the origin) linear separators and analyze its error convergence when labels are corrupted by noise. We show that when the imposed noise satisfies the Tsybakov low noise condition (Mammen, Tsybakov, and others 1999; Tsyb…

Framework for robust control in cooperative systems with uncertain common noise.

Study optimizes resource allocation in noisy systems for better control.

Unified Bayesian model explains in-context learning and activation steering in LLMs.

LineFlow is a framework for training RL agents to control production lines.

Active learning seeks to build the best possible model with a budget of labelled data by sequentially selecting the next point to label. However the training set is no longer \textit{iid}, violating the conditions required by existing consistency results. Inspired by the success of Stone's Theorem we aim to regain cons…

Bayesian adaptive designs can be biased by active learning, especially with misspecified models.

Optimizes control of noisy discrete systems without system matrix knowledge.

We present for the first time an asymptotic convergence analysis of two time-scale stochastic approximation driven by `controlled' Markov noise. In particular, both the faster and slower recursions have non-additive controlled Markov noise components in addition to martingale difference noise. We analyze the asymptotic…

Robust $Q$-learning for mean-field control under Wasserstein uncertainty

A new protocol corrects confounding effects to measure alignment-induced activation shifts accurately.

Study learns linear utility functions from comparisons, showing learnability gaps between passive and active learning.

Brain source imaging is an important method for noninvasively characterizing brain activity using Electroencephalogram (EEG) or Magnetoencephalography (MEG) recordings. Traditional EEG/MEG Source Imaging (ESI) methods usually assume that either source activity at different time points is unrelated, or that similar spat…

Agents learn and control complex mechanical systems through shared memories.

PenduMAV is a 6-input omnidirectional MAV without internal forces.