February 2026

We study distributionally robust online learning, where a risk-averse learner updates decisions sequentially to guard against worst-case distributions drawn from a Wasserstein ambiguity set centered at past observations. While this paradigm is well understood in the offline setting through Wasserstein Distributionally Robust Optimization (DRO), its online extension poses significant challenges in both convergence and computation. In this paper, we address these challenges. First, we formulate the problem as an online saddle-point stochastic game between a decision maker and […]

Ver mais

The universal approximation theorem establishes that neural networks can approximate any continuous function on a compact set. Later works in approximation theory provide quantitative approximation rates for ReLU networks on the class of $α$-Hölder functions $f: [0,1]^N to mathbb{R}$. The goal of this paper is to provide similar quantitative approximation results in the context of group equivariant learning, where the learned $α$-Hölder function is known to obey certain group symmetries. While there has been much interest in the […]

Ver mais

Deep neural networks (DNNs) have been increasingly explored for receiver design because they can handle complex environments without relying on explicit channel models. Nevertheless, because communication channels change rapidly, their distributions can shift over time, often making periodic retraining necessary. This paper proposes a zero-overhead online and continual learning framework for orthogonal frequency-division multiplexing (OFDM) neural receivers that directly detect the soft bits of received signals. Unlike conventional fine-tuning methods that rely on dedicated training intervals or full […]

Ver mais

Graph self-supervised learning (GSSL) has demonstrated strong potential for generating expressive graph embeddings without the need for human annotations, making it particularly valuable in domains with high labeling costs such as molecular graph analysis. However, existing GSSL methods mostly focus on node- or edge-level information, often ignoring chemically relevant substructures which strongly influence molecular properties. In this work, we propose Graph Semantic Predictive Network (GraSPNet), a hierarchical self-supervised framework that explicitly models both atomic-level and fragment-level semantics. GraSPNet […]

Ver mais

Published on February 8, 2026 9:44 AM GMT If you’re a woman interested in preserving your fertility window beyond its natural close in your early 40s, egg freezing is one of your best options. But if you rely on your doctor to tell you when to freeze them, you will likely be doing yourself and your future prospects for a family a disservice. The female reproductive system is one of the fastest aging parts of human biology. But […]

Ver mais

I am training TD3 on MetaDrive with 10 scenes. First, I trained on all 10 scenes together for 100k total steps (standard setup, num_scenarios=10, one learn call). Performance was very poor. Then I trained 10 scenes sequentially with 100k per scene (scene 0 → 100k, then scene 1 → 100k, …). Total 1M steps. Still poor. Then I selected a subset of scenes: [0, 1, 3, 6, 7, 8]. Then I selected a subset of scenes: [0, 1, […]

Ver mais

Background: Childhood and adolescent overweight and obesity remain major public health concerns in the United States and are shaped by behavioral, household, and community factors. Their joint predictive structure at the population level remains incompletely characterized. Objectives: The study aims to identify multilevel predictors of overweight and obesity among U.S. adolescents and compare the predictive performance, calibration, and subgroup equity of statistical, machine-learning, and deep-learning models. Data and Methods: We analyze 18,792 children aged 10-17 years from the […]

Ver mais