arXiv research

GACELA fills long gaps in musical audio with a GAN and context conditioning.

Proves effective slope gaps for lattice surfaces.

Sparse attention model reduces long-context inference time with exponential accuracy guarantees.

Generative adversarial network improves audio inpainting for long gaps.

LLapDiff models irregular multivariate time series without step-by-step integration.

In this paper we construct compact manifolds with fixed boundary geometry which admit Riemannian metrics of unit volume with arbitrarily large Steklov spectral gap. We also study the effect of localized conformal deformations that fix the boundary geometry. For instance, we prove that it is possible to make the spectra…

New theorem shows curvature concentration depends linearly on volume ratio.

A Gaussian mixture model improves generalization for long-tailed data.

Study hot spots on warped product manifolds and infinite cones.

As a testament to their success, the theory of random forests has long been outpaced by their application in practice. In this paper, we take a step towards narrowing this gap by providing a consistency result for online random forests.

New approach shapes error distribution in long-term forecasting.

Study reveals $1/f$ noise in signals made from nonoverlapping rectangular pulses.

Price gap, defined as the logarithmic price difference between the first two occupied price levels on the same side of a limit order book (LOB), is a key determinant of market depth, which is one of the dimensions of liquidity. However, the properties of price gaps have not been thoroughly studied due to the less avail…

Study shows exponential gap in sample complexity between noisy and non-noisy recurrent neural networks.

New method fuses optical and SAR data to fill LAI gaps during cloudy periods.

TimeBridge addresses non-stationarity in long-term time series forecasting.

Neural ARFIMA model improves exchange rate forecasting for BRIC economies.

Unified framework for fair pricing in long-term insurance products.

The paper addresses estimating long-term treatment effects with monotone missing data.

TAET tackles long-tailed distributions in adversarial robustness.

Improved Mamba model for long-range sequence tasks.

This article presents the use of Answer Set Programming (ASP) to mine sequential patterns. ASP is a high-level declarative logic programming paradigm for high level encoding combinatorial and optimization problem solving as well as knowledge representation and reasoning. Thus, ASP is a good candidate for implementing p…

ELM improves neural model embeddings for long-tail learning.

Chaos in cerebellar cells enhances complexity of neural patterns.

A new method simulates a lazy version of a Markov chain for empirical inference.

Persistent homology enhances graph classification by capturing long-range graph properties.

Unified framework for critical scaling of inverse temperature in self-attention.

The study confirms a conjecture about Kähler manifolds with quasi-negative curvature.

This paper examines multifractal dynamics in cryptocurrencies using two methodologies.

Novel approach predicts long-term seasonal component of electricity prices for improved forecasting.

Prediction markets and crypto options show persistent pricing gaps.

Of concern is the study of the long-time existence of solutions to the Euler--Arnold equation of the right-invariant $H^{3/2}$-metric on the diffeomorphism group of the circle. In previous work by Escher and Kolev it has been shown that this equation admits long-time solutions if the order $s$ of the metric is greater …

New convergence rates for shuffling gradient methods without strong convexity.

The effectiveness of model-based versus model-free methods is a long-standing question in reinforcement learning (RL). Motivated by recent empirical success of RL on continuous control tasks, we study the sample complexity of popular model-based and model-free algorithms on the Linear Quadratic Regulator (LQR). We show…

Adaptive Nucleus Truncation Improves Long-Form Reasoning

We consider the setup of stochastic multi-armed bandits in the case when reward distributions are piecewise i.i.d. and bounded with unknown changepoints. We focus on the case when changes happen simultaneously on all arms, and in stark contrast with the existing literature, we target gap-dependent (as opposed to only g…

RNNs struggle with in-context retrieval, while Transformers excel.

We consider the estimation of large covariance and precision matrices from high-dimensional sub-Gaussian or heavier-tailed observations with slowly decaying temporal dependence. The temporal dependence is allowed to be long-range so with longer memory than those considered in the current literature. We show that severa…

Improves spatio-temporal forecasting by reducing errors between training and inference.

New algorithm reduces regret in combinatorial causal bandits without graph structure.

The liberalization of electricity markets and the development of renewable energy sources has led to new challenges for decision makers. These challenges are accompanied by an increasing uncertainty about future electricity price movements. The increasing amount of papers, which aim to model and predict electricity pri…

ARBITER learns SPX-VIX term structures without arbitrage constraints.

MambaLRP enhances Mamba models' explainability and performance.

Time-related features improve time series forecasting models.

New framework uses dynamics to justify Gaussian process for turbulent flows.

Long-term lane change prediction model predicts maneuvers with 75% accuracy.

Self-supervised learning performs better than supervised learning on imbalanced datasets.

New optimizer SF-NorMuon matches tuned AdamW across various horizons.