arXiv:2603.02533v1 Announce Type: cross Abstract: The focal-loss has become a widely used alternative to cross-entropy in class-imbalanced classification problems, particularly in computer vision. Despite its empirical success, a systematic information-theoretic study of the focal-loss remains incomplete. In this work, we adopt a distributional viewpoint and study the focal-entropy, a focal-loss analogue of the cross-entropy. Our analysis establishes conditions for finiteness, convexity, and continuity of the focal-entropy, and provides various asymptotic characterizations. We prove the existence and uniqueness of […]

Ver mais

arXiv:2403.01673v2 Announce Type: replace Abstract: For Multivariate Time Series Forecasting (MTSF), recent deep learning applications show that univariate models frequently outperform multivariate ones. To address the difficiency in multivariate models, we introduce a method to Construct Auxiliary Time Series (CATS) that functions like a 2D temporal-contextual attention mechanism, which generates Auxiliary Time Series (ATS) from Original Time Series (OTS) to effectively represent and incorporate inter-series relationships for forecasting. Key principles of ATS – continuity, sparsity, and variability – […]

Ver mais

arXiv:2603.16958v1 Announce Type: new Abstract: Vision-Language Models (VLMs) are increasingly applied to robotic perception and manipulation, yet their ability to infer physical properties required for manipulation remains limited. In particular, estimating the mass of real-world objects is essential for determining appropriate grasp force and ensuring safe interaction. However, current VLMs lack reliable mass reasoning capabilities, and most existing benchmarks do not explicitly evaluate physical quantity estimation under realistic sensing conditions. In this work, we propose PhysQuantAgent, a framework […]

Ver mais

I’m working on a project where I’ll be fine-tuning LLMs with GRPO on a 170K-sample dataset for explainable LJP (legal judgment prediction, where the model predicts case outcomes and generates step-by-step reasoning citing the facts). I’m considering models like GPT OSS 20B or Qwen 3.5 27B, with a slight preference for Qwen 3.5 27B because of its strong reasoning capabilities. I recently obtained a 96GB VRAM workstation (RTX PRO 6000) to handle the RL rollouts, which should give […]

Ver mais

arXiv:2603.28201v1 Announce Type: cross Abstract: We revisit the standard perturbation-based approach of Abernethy et al. (2008) in the context of unconstrained Bandit Linear Optimization (uBLO). We show the surprising result that in the unconstrained setting, this approach effectively reduces Bandit Linear Optimization (BLO) to a standard Online Linear Optimization (OLO) problem. Our framework improves on prior work in several ways. First, we derive expected-regret guarantees when our perturbation scheme is combined with comparator-adaptive OLO algorithms, leading to new […]

Ver mais

Federated learning (FL) faces two structural tensions: gradient sharing enables data-reconstruction attacks, while non-IID client distributions degrade aggregation quality. We introduce PTOPOFL, a framework that addresses both challenges simultaneously by replacing gradient communication with topological descriptors derived from persistent homology (PH). Clients transmit only 48-dimensional PH feature vectors-compact shape summaries whose many-to-one structure makes inversion provably ill-posed-rather than model gradients. The server performs topology-guided personalised aggregation: clients are clustered by Wasserstein similarity between their PH diagrams, intra-cluster models […]

Ver mais

Hi everyone, I recently wrote this whitepaper https://github.com/RippnerLabs/meridian-link/blob/main/whitepaper/whitepaper.pdf And i’m blocked on publishing to arXiv, due to lack of endorsement for DC (Distributed, Parallel, and Cluster Computing) Can anyone please let support with this endorsement. (Jayanth Kumar Morem should forward this email to someone who’s registered as an endorser for the cs.DC (Distributed, Parallel, and Cluster Computing) subject class of arXiv.) Jayanth Kumar Morem requests your endorsement to submit an article to the cs.DC section of arXiv. To […]

Ver mais

Intro: Stock Price Prediction, Machine Learning, and Quantum ML Today, we’re diving into the intersection of quantum computing and machine learning, exploring quantum machine learning and its application in stock price prediction. Our main goal is to compare the performance of a quantum neural network for stock price time series forecasting with a simple single-layer MLP. To facilitate this project, we’ll be utilizing the Historical API endpoint offered by Financial Modeling Prep (FMP) for reliable and accurate data which is […]

Ver mais

arXiv:2604.01501v1 Announce Type: cross Abstract: Causal mediation analysis provides techniques for defining and estimating effects that may be endowed with mechanistic interpretations. With many scientific investigations seeking to address mechanistic questions, causal direct and indirect effects have garnered much attention. The natural direct and indirect effects, the most widely used among such causal mediation estimands, are limited in their practical utility due to stringent identification requirements. Accordingly, considerable effort has been invested in developing alternative direct and indirect […]

Ver mais