arXiv:2604.26558v1 Announce Type: new Abstract: Deep learning methods have proved highly effective for classification and image recognition problems. In this paper, we ask whether this success can be transferred to hypothesis testing: if a neural network can distinguish, for example, an image of a handwritten digit from another, can it also distinguish an “image of a sample” (such as a scatter plot) generated under a given statistical model from one generated outside that model? Motivated by this idea, […]

Ver mais

In The Gay Science (1882), German philosopher Friedrich Nietzsche famously proclaimed the death of God. Recognizing the enormous implications of secularization and the uprooting of Christianity’s “fundamental concept” (faith in God) and the resulting moral confusion, he exclaimed: “God is dead! Continue Reading…

Ver mais

arXiv:2603.04807v1 Announce Type: new Abstract: We study how architectural inductive bias reshapes the implicit regularization induced by the edge-of-stability phenomenon in gradient descent. Prior work has established that for fully connected networks, the strength of this regularization is governed solely by the global input geometry; consequently, it is insufficient to prevent overfitting on difficult distributions such as the high-dimensional sphere. In this paper, we show that locality and weight sharing fundamentally change this picture. Specifically, we prove that […]

Ver mais

arXiv:2603.00968v1 Announce Type: new Abstract: The Nash-Sutcliffe efficiency ($text{NSE}$) is a widely used, positively oriented relative measure for evaluating forecasts across multiple time series. However, it lacks a decision-theoretic foundation for this purpose. To address this, we examine its negatively oriented counterpart, which we refer to as Nash-Sutcliffe loss, defined as $L_{text{NS}} = 1 – text{NSE}$. We prove that $L_{text{NS}}$ is strictly consistent for an elicitable and identifiable multi-dimensional functional, which we name the Nash-Sutcliffe functional. This functional […]

Ver mais

Traditional RL algorithms like Proximal Policy Optimization (PPO) typically train on the entire rollout buffer, operating under the assumption that all generated episodes provide a beneficial optimization signal. However, these episodes frequently contain noisy or unfaithful reasoning, which can degrade model performance and slow down training. In this paper, we propose textbf{Influence-Guided PPO (I-PPO)}, a novel framework that integrates data attribution into the RL post-training loop. By calculating an influence score for each episode using a gradient-based approximation, […]

Ver mais

arXiv:2602.07206v1 Announce Type: new Abstract: Softmax Loss (SL) is being increasingly adopted for recommender systems (RS) as it has demonstrated better performance, robustness and fairness. Yet in implicit-feedback, a single global temperature and equal treatment of uniformly sampled negatives can lead to brittle training, because sampled sets may contain varying degrees of relevant or informative competitors. The optimal loss sharpness for a user-item pair with a particular set of negatives, can be suboptimal or destabilising for another with […]

Ver mais

arXiv:2601.02573v1 Announce Type: new Abstract: Credit risk assessment is essential in the financial sector, but has traditionally depended on costly feature-based models that often fail to utilize all available information in raw credit records. This paper introduces LendNova, the first practical automated end-to-end pipeline for credit risk assessment, designed to utilize all available information in raw credit records by leveraging advanced NLP techniques and language models. LendNova transforms risk modeling by operating directly on raw, jargon-heavy credit bureau […]

Ver mais

This paper introduces a new framework for recovering causal graphs from observational data, leveraging the observation that the distribution of an effect, conditioned on its causes, remains invariant to changes in the prior distribution of those causes. This insight enables a direct test for potential causal relationships by checking the variance of their corresponding effect-cause conditional distributions across multiple downsampled subsets of the data. These subsets are selected to reflect different prior cause distributions, while preserving the effect-cause […]

Ver mais

Post-training Large Language Models (LLMs) for long-horizon agentic tasks—such as software engineering, web browsing, and complex tool use—presents a persistent trade-off between computational efficiency and model generalization. While Supervised Fine-Tuning (SFT) is computationally inexpensive, it frequently suffers from out-of-domain (OOD) performance degradation and struggles to generalize beyond its training distribution. Conversely, end-to-end reinforcement learning (E2E RL) typically preserves OOD capabilities and achieves high in-domain accuracy, but it incurs massive compute costs due to the necessity of repeated, many-turn […]

Ver mais