arXiv:2509.10529v1 Announce Type: new Abstract: Continual learning — the ability to acquire knowledge incrementally without forgetting previous skills — is fundamental to natural intelligence. While the human brain excels at this, artificial neural networks struggle with “catastrophic forgetting,” where learning…
arXiv:2504.20022v2 Announce Type: replace-cross Abstract: Multilingual Large Language Models (LLMs) have demonstrated significant effectiveness across various languages, particularly in high-resource languages such as English. However, their performance in terms of factual accuracy across other low-resource languages, especially Indic languages, remains…
arXiv:2509.10530v1 Announce Type: new Abstract: Transformer models based on the Mixture of Experts (MoE) architecture have made significant progress in long-sequence modeling, but existing models still have shortcomings in computational efficiency and the ability to capture long-range dependencies, especially in…
arXiv:2508.07982v2 Announce Type: replace-cross Abstract: We propose a novel kernel-based nonparametric two-sample test, employing the combined use of kernel mean and kernel covariance embedding. Our test builds on recent results showing how such combined embeddings map distinct probability measures to…
arXiv:2509.10531v1 Announce Type: new Abstract: Portfolio optimization is essential for balancing risk and return in financial decision-making. Deep Reinforcement Learning (DRL) has stood out as a cutting-edge tool for portfolio optimization that learns dynamic asset allocation using trial-and-error interactions. However,…
arXiv:2509.12154v1 Announce Type: cross Abstract: The first part of this paper studies the evolution of gradient flow for homogeneous neural networks near a class of saddle points exhibiting a sparsity structure. The choice of these saddle points is motivated from…
arXiv:2509.11070v1 Announce Type: new Abstract: We develop a stochastic approximation framework for learning nonlinear operators between infinite-dimensional spaces utilizing general Mercer operator-valued kernels. Our framework encompasses two key classes: (i) compact kernels, which admit discrete spectral decompositions, and (ii) diagonal…
arXiv:2509.12031v1 Announce Type: cross Abstract: In this paper, we examine the problem of sampling from log-concave distributions with (possibly) superlinear gradient growth under kinetic (underdamped) Langevin algorithms. Using a carefully tailored taming scheme, we propose two novel discretizations of the…
arXiv:2508.12426v2 Announce Type: replace-cross Abstract: The minimum density power divergence estimator (MDPDE) has gained significant attention in the literature of robust inference due to its strong robustness properties and high asymptotic efficiency; it is relatively easy to compute and can…
arXiv:2506.19010v2 Announce Type: replace Abstract: Causal decomposition analysis aims to assess the effect of modifying risk factors on reducing social disparities in outcomes. Recently, this analysis has incorporated individual characteristics when modifying risk factors by utilizing optimal treatment regimes (OTRs).…
