arXiv research

Algorithm detects changes online using expert tracking.

In this paper, we propose a hierarchical feature-aware tracking framework for efficient visual tracking. Recent years, ensembled trackers which combine multiple component trackers have achieved impressive performance. In ensembled trackers, the decision of results is usually a post-event process, i.e., tracking result …

In this paper, we consider the problem of prediction with expert advice in dynamic environments. We choose tracking regret as the performance metric and develop two adaptive and efficient algorithms with data-dependent tracking regret bounds. The first algorithm achieves a second-order tracking regret bound, which impr…

HS-MoE selects sparse experts using adaptive priors and data-adaptive gating.

This work uses SVM to identify track component failures in AC Track Circuits.

Adaptive Bayesian learning aggregates experts to improve performance.

When dealing with time series with complex non-stationarities, low retrospective regret on individual realizations is a more appropriate goal than low prospective risk in expectation. Online learning algorithms provide powerful guarantees of this form, and have often been proposed for use with non-stationary processes …

Deep learning on an edge device requires energy efficient operation due to ever diminishing power budget. Intentional low quality data during the data acquisition for longer battery life, and natural noise from the low cost sensor degrade the quality of target output which hinders adoption of deep learning on an edge d…

We consider prediction with expert advice under the log-loss with the goal of deriving efficient and robust algorithms. We argue that existing algorithms such as exponentiated gradient, online gradient descent and online Newton step do not adequately satisfy both requirements. Our main contribution is an analysis of th…

Detects project management anti-patterns using code and issue data.

C-FAR automates clustering assessment for neural tracking.

A digital twin for multi-scale systems uses physics-based and machine learning models.

We consider a variation on the problem of prediction with expert advice, where new forecasters that were unknown until then may appear at each round. As often in prediction with expert advice, designing an algorithm that achieves near-optimal regret guarantees is straightforward, using aggregation of experts. However, …

In an era of ubiquitous large-scale streaming data, the availability of data far exceeds the capacity of expert human analysts. In many settings, such data is either discarded or stored unprocessed in datacenters. This paper proposes a method of online data thinning, in which large-scale streaming datasets are winnowed…

This paper considers the challenge of evaluating a set of classifiers, as done in shared task evaluations like the KDD Cup or NIST TREC, without expert labels. While expert labels provide the traditional cornerstone for evaluating statistical learners, limited or expensive access to experts represents a practical bottl…

A new framework enhances binaural audio for moving talkers.

PCGS-TF uses a Transformer to adaptively control expert switching in non-stationary environments.

Study monopole h-invariants from a topological viewpoint.

SoccerCPD detects tactical changes in soccer matches using spatiotemporal tracking data.

Auto-CEI improves LLM reasoning by balancing assertiveness and conservativeness.

Method predicts NBA players' multi-modal movement trajectories.

New algorithms achieve optimal regret in sliding window model with limited memory.

In this paper, we study online convex optimization in dynamic environments, and aim to bound the dynamic regret with respect to any sequence of comparators. Existing work have shown that online gradient descent enjoys an $O(\sqrt{T}(1+P_T))$ dynamic regret, where $T$ is the number of iterations and $P_T$ is the path-le…

Near-optimal per-action regret bounds for sleeping bandits are derived.

LR-Robot accelerates SLRs by combining expert oversight and AI, revealing trends and patterns in financial research.

The study examines how language models learn to represent the world, identifying conditions for ecological veridicality.

Semantic code search is the task of retrieving relevant code given a natural language query. While related to other information retrieval tasks, it requires bridging the gap between the language used in code (often abbreviated and highly technical) and natural language more suitable to describe vague concepts and ideas…

Internet of things (IoT) applications have become increasingly popular in recent years, with applications ranging from building energy monitoring to personal health tracking and activity recognition. In order to leverage these data, automatic knowledge extraction - whereby we map from observations to interpretable stat…

Deep Neural Networks (DNNs) are universal function approximators providing state-of- the-art solutions on wide range of applications. Common perceptual tasks such as speech recognition, image classification, and object tracking are now commonly tackled via DNNs. Some fundamental problems remain: (1) the lack of a mathe…

RL approach for target tracking with unknown dynamics and sensor control.

New train tracks for complex homeomorphisms found.

New method uses cluster shapes to improve track finding in particle collisions.

New approach optimizes policies in adversarial MDPs using adversarial learning.

This paper optimizes object tracking on edge devices with small matrices.

Multi-expert L2D underfits more severely, requiring new methods.

A DRL-based strategy improves vehicle tracking accuracy while saving energy.

Paper introduces TAP-Vid, a benchmark for tracking any point in videos.

The efficiency of a modern economy depends on what we call the Value-Tracking Hypothesis: that market prices of key assets broadly track some underlying value. This can be expected if a sufficient weight of market participants are valuation-based traders, buying and selling an asset when its price is, respectively, bel…

We show that the subsurface projection of a train track splitting sequence is an unparameterized quasi-geodesic in the curve complex of the subsurface. For the proof we introduce induced tracks, efficient position, and wide curves. This result is an important step in the proof that the disk complex is Gromov hyperbolic…

Train track automata for fully irreducible elements in Out(F_r).

Detects harmful distribution shifts in deployed models without false alarms.

Dynamic tracking error framework shows similar performance but varying volatility across different constraints.

Paper improves Lasso for S&P500 index tracking with post-selection inference.

Bayesian approach for constructing and rebalancing sparse index-tracking portfolios.

Automated method selects eye tracking variables for categorization tasks.

We propose a new Bayesian tracking and parameter learning algorithm for non-linear non-Gaussian multiple target tracking (MTT) models. We design a Markov chain Monte Carlo (MCMC) algorithm to sample from the posterior distribution of the target states, birth and death times, and association of observations to targets, …

TENP prunes experts and neurons in Mixture-of-Experts models for efficient deployment.

A method to select important experts for Gaussian processes to balance computational efficiency and uncertainty quantification.