A new tracking method using expert selection and feature fusion.
problem Efficient visual tracking with multiple component trackers.
method Pre-event selection of experts based on past performance and feature fusion.
result Superior performance compared to ensembled trackers on public datasets.
Algorithm detects changes online using expert tracking.
problem Online change point detection in nonparametric settings.
method Sequential score function estimation and tracking the best expert approach.
result Algorithm performs well in artificial and real-world data.
Two adaptive algorithms improve tracking regret in dynamic expert advice problems.
problem Prediction with expert advice in dynamic environments.
method Developed two adaptive and efficient algorithms using online mirror descent framework.
result Achieved data-dependent tracking regret bounds for both algorithms.
Prod algorithm improves robustness and efficiency in log-loss prediction.
problem Efficient and robust algorithms for log-loss prediction under expert advice.
method Analysis of Prod algorithm for mixtures of experts with log-loss.
result Prod algorithm provides linear-time bound independent of largest loss and gradient.
HS-MoE selects sparse experts using adaptive priors and data-adaptive gating.
problem Sparse expert selection in mixture-of-experts architectures.
method Combines horseshoe prior with input-dependent gating for data-adaptive sparsity.
result Data-adaptive sparsity in expert usage.
Edge device deep learning improved with noise handling model.
problem Noise and low quality data degrade deep learning performance on edge devices.
method Mixture of Pre-processing Experts (MoPE) model with adversarially trained autoencoder.
result The MoPE model achieves better accuracy on noisy images without sacrificing clean image accuracy.
This work uses SVM to identify track component failures in AC Track Circuits.
problem Detecting and identifying specific track component failures in AC Track Circuits.
method Applied SVM classifier to STDS track circuit data.
result Successfully classified 15 different track component failures.
Adaptive Bayesian learning aggregates experts to improve performance.
problem Bayesian online learning's performance depends on inferential choices.
method Treat Bayesian update rules as experts and aggregate them based on sequential predictive losses.
result The aggregate competes with the best expert in hindsight at a low aggregation cost.
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 …
Paper develops adaptive learning method to minimize dynamic regret in dynamic environments.
problem Bounding dynamic regret in online convex optimization for dynamic environments.
method Adaptive Learning for Dynamic Environment (Ader) method, combining multiple experts and an expert-tracking algorithm.
result Achieves optimal O ( T ( 1 + P T ) ) O(\sqrt{T(1+P_T)}) O ( T ( 1 + P T ) ) dynamic regret, closing the gap from previous O ( T ( 1 + P T ) ) O(\sqrt{T(1+P_T)}) O ( T ( 1 + P T ) ) lower bound. Detects project management anti-patterns using code and issue data.
problem Detecting project management anti-patterns requires expert judgment and is expensive.
method Convert descriptions to detectable metrics, quantify deviations, and optimize patterns.
result Automatic calibration enhances pattern detection and severity assessment.
C-FAR automates clustering assessment for neural tracking.
problem Manual assessment of clusters by humans is slow and impractical for large datasets.
method C-FAR uses automated feedback queries to select optimal clustering from multiple algorithms.
result C-FAR produces near-perfect clustering on simulated neural data.
A digital twin for multi-scale systems uses physics-based and machine learning models.
problem Lack of application-specific details in digital twin technology.
method Strategically separates into physics-based and data-driven models; uses mixture of experts with Gaussian Process.
result Robust and accurate predictions at future time-steps for multi-scale systems.
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.
problem Real-time binaural audio enhancement for moving sound sources.
method Mixture-of-experts framework combining multiple binaural filters.
result Dynamic spatial audio rendering adapts to moving talkers.
PCGS-TF uses a Transformer to adaptively control expert switching in non-stationary environments.
problem Static regret is insufficient for strictly online prediction in non-stationary settings.
method Policy-Controlled Generalized Share (PCGS) with a Transformer as an update controller.
result PCGS-TF achieves the lowest dynamic regret in non-stationary families and expert pools.
Study monopole h-invariants from a topological viewpoint.
problem Understanding the h-invariants of 3-manifolds.
method Using Lidman and Manolescu's description of monopole Floer homology.
result Prove several properties of the h-invariants.
SoccerCPD detects tactical changes in soccer matches using spatiotemporal tracking data.
problem Detecting consistent team formations in fluid sports like soccer.
method Two-step change-point detection: formation and role changes.
result Accurately detects tactical changes and estimates formation and role assignments.
Auto-CEI improves LLM reasoning by balancing assertiveness and conservativeness.
problem Hallucinations and laziness in LLM reasoning tasks.
method Expert Iteration explores reasoning trajectories, guiding incorrect paths back on track and promoting appropriate 'I don't know' responses.
result Auto-CEI achieves superior alignment in logical reasoning, mathematics, and planning tasks.
Method predicts NBA players' multi-modal movement trajectories.
problem Understanding NBA players' decision-making during games.
method LSTM-based architecture with multi-modal loss function.
result Method outperforms state-of-the-art in predicting realistic trajectories.
New algorithms achieve optimal regret in sliding window model with limited memory.
problem Experts problem in the sliding window model with limited information.
method 2 queries, polylog(nT) memory, exponential improvement on memory.
result Achieve optimal regret of sqrt(nW)polylog(nT) with 2 queries and polylog(nT) memory.
New approach learns traffic behavior from unlabelled video.
problem Learning from demonstration in settings with unlabelled raw video data.
method Calibrates camera, detects objects, tracks them, and uses trajectories for LfD.
result Can learn traffic behavior from raw video without additional expert knowledge.
Near-optimal per-action regret bounds for sleeping bandits are derived.
problem Optimizing performance in sleeping bandits where arms and losses are chosen by an adversary.
method Directly minimizing per-action regret using generalized versions of EXP3, EXP3-IX, and FTRL with Tsallis entropy.
result Near-optimal bounds of order O ( T A ln K ) O(\sqrt{TA\ln{K}}) O ( T A ln K ) and O ( T A K ) O(\sqrt{T\sqrt{AK}}) O ( T A K ) are obtained. LR-Robot accelerates SLRs by combining expert oversight and AI, revealing trends and patterns in financial research.
problem Manual SLRs are impractical due to the scale and complexity of modern financial research.
method Domain experts define taxonomies and constraints, LLMs execute classification, and human evaluation ensures reliability.
result AI can understand and synthesize literature, revealing trends and core research directions.
The study examines how language models learn to represent the world, identifying conditions for ecological veridicality.
problem Understanding when language models learn to represent the world accurately and how this learning process can fail.
method Analyzes the Bayes-optimal next-token cross-entropy decomposition and the role of training ecology in shaping model representations.
result The minimum-complexity zero-excess solution is the quotient partition by training equivalence, and this solution is not preserved in in-context learning or per-task adaptation.
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.
problem Tracking an unknown target with sensor control.
method Track-MDP formulation for RL, compared with POMDP.
result Optimal RL policy tracks all target paths with certainty.
Challenge evaluates semantic code search using annotated corpus.
problem Evaluating relevant code from natural language queries.
method Release of CodeSearchNet Corpus and expert annotations.
result 99 queries with 4k relevance annotations for evaluation.
New train tracks for complex homeomorphisms found.
problem Existence of irreducible train tracks for pseudo-Anosov homeomorphisms.
method Starting from a veering triangulation, identify and modify branches to bypass obstructions.
result Construction of invariant train tracks with irreducible transition matrix.
New approach optimizes policies in adversarial MDPs using adversarial learning.
problem Optimizing policies in adversarial Markov decision processes.
method Adversarial learning on advantage functions, extending previous reductions.
result Stronger regret criteria and performance guarantees for policy optimization.
New method uses cluster shapes to improve track finding in particle collisions.
problem Combining timing and additional detector information for efficient track finding.
method Neural networks to analyze cluster shapes for track seeding.
result Cluster shapes reduce fake combinatorial backgrounds while maintaining high track efficiency.
Value-tracking in financial markets breaks down when non-valuation-based traders dominate.
problem Understanding the threshold for value-tracking in financial markets.
method Simple discrete-time model to show how non-valuation-based traders can cause tracking errors.
result A threshold above which value-tracking breaks down without changes in asset value.
This paper optimizes object tracking on edge devices with small matrices.
problem Efficiently tracking objects in video sequences on edge devices with small matrices.
method Parallelized a Simple Online and Real-time Tracking (SORT) application on shared-memory multicores.
result Throughput-based parallelization technique outperforms multi-threading for small matrices.
Multi-expert L2D underfits more severely, requiring new methods.
problem Underfitting in multi-expert L2D settings.
method PiCCE (Pick the Confident and Correct Expert), a surrogate-based method.
result PiCCE effectively reduces multi-expert L2D to a single-expert-like problem, resolving underfitting.
A DRL-based strategy improves vehicle tracking accuracy while saving energy.
problem Enhancing vehicle tracking accuracy in WSNs without increasing energy consumption.
method Decentralized strategy with dynamic reinforcement learning to adjust sensing areas.
result Simulation results demonstrate superior performance of DRL-aided design.
Paper introduces TAP-Vid, a benchmark for tracking any point in videos.
problem Tackles the problem of tracking arbitrary physical points on surfaces over longer video clips.
method Formalizes the problem as TAP, introduces TAP-Vid benchmark, uses crowdsourced pipeline with optical flow estimates, proposes TAP-Net model.
result TAP-Net outperforms all prior methods on TAP-Vid benchmark when trained on synthetic data.
Detects harmful distribution shifts in deployed models without false alarms.
problem Detecting harmful distribution shifts in deployed models without false alarms.
method Sequential tools for testing if the difference between source and target distributions leads to a significant increase in a risk function.
result Demonstrated the efficacy of the proposed framework through extensive empirical studies.
Study on VIX futures portfolios to track VIX index, finding dynamic strategy superior.
problem Tracking VIX index with VIX futures lagging.
method Optimization methods for static portfolios, dynamic trading strategy for VIX futures.
result Dynamic trading strategy outperforms static portfolios and VXX in tracking VIX.
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).
problem Understanding fully irreducible elements in Out(F_r).
method Describing train track automata and geodesics in Outer Space.
result Geodesics in Culler-Vogtmann Outer Space for fully irreducible elements.
A novel tracking method for dense honeybee colonies using pixel personality.
problem Tracking large numbers of densely-arranged, interacting objects in a 2D environment.
method Segmentation-based object detection followed by adaptive object recognition through visual appearance.
result Reconstructed ~46% of trajectories in 5 minutes and 71% of tracks for at least 2 minutes.
Dynamic tracking error framework shows similar performance but varying volatility across different constraints.
problem Differences in governance parameters between Total Portfolio Approach and Strategic Asset Allocation.
method Portfolio simulations using U.S. equity and bond data from 2000 to 2026, spanning 2004 to 2026.
result Realized tracking error volatility varies 12-fold across different constraints, with costs highest during crises.
A new neural network approach reduces tracking error in index replication.
problem Efficiently replicating an index with cardinality constraints.
method Reparametrisation and stochastic neural networks for optimisation.
result Our model achieves the lowest tracking error compared to benchmarks.
Modeling self-tracking data identifies subtypes of endometriosis.
problem No known biomarkers for endometriosis, highly enigmatic condition.
method Mixed-membership models on self-tracking data.
result Identifies potential subtypes robust to tracking variations.
Paper improves Lasso for S&P500 index tracking with post-selection inference.
problem Index tracking for S&P500 with many applications.
method Used Lasso for dimension reduction and post-selection inference.
result Lasso method for S&P500 index tracking shows high performance.