arXiv:2206.13405v2 Announce Type: replace-cross Abstract: Robustness is a fundamental pillar of Machine Learning (ML) classifiers, substantially determining their reliability. Methods for assessing classifier robustness are therefore essential. In this work, we address the challenge of evaluating corruption robustness in a way that allows comparability and interpretability on a given dataset. We propose a test data augmentation method that uses a robustness distance $epsilon$ derived from the datasets minimal class separation distance. The resulting MSCR (minimal separation corruption robustness) […]

Ver mais

arXiv:2601.04272v1 Announce Type: new Abstract: The paper introduces a basic logic of knowledge and abduction by extending Levesque logic of only-knowing with an abduction modal operator defined via the combination of basic epistemic concepts. The upshot is an alternative approach to abduction that employs a modal vocabulary and explores the relation between abductive reasoning and epistemic states of only knowing. Furthermore, by incorporating a preferential relation into modal frames, we provide a non-monotonic extension of our basic framework […]

Ver mais

[Updated on 2018-09-30: thanks to Yoonju, we have this post translated in Korean!] [Updated on 2019-04-18: this post is also available on arXiv.] Generative adversarial network (GAN) has shown great results in many generative tasks to replicate the real-world rich content such as images, human language, and music. It is inspired by game theory: two models, a generator and a critic, are competing with each other while making each other stronger at the same time. However, it is […]

Ver mais

arXiv:2601.12120v1 Announce Type: cross Abstract: Instrumental variable based estimation of a causal effect has emerged as a standard approach to mitigate confounding bias in the social sciences and epidemiology, where conducting randomized experiments can be too costly or impossible. However, justifying the validity of the instrument often poses a significant challenge. In this work, we highlight a problem generally neglected in arguments for instrumental variable validity: the presence of an ”aggregate treatment variable”, where the treatment (e.g., education, […]

Ver mais

Connections between statistical mechanics and machine learning have repeatedly proven fruitful, providing insight into optimization, generalization, and representation learning. In this work, we follow this tradition by leveraging results from non-equilibrium thermodynamics to formalize curriculum learning in reinforcement learning (RL). In particular, we propose a geometric framework for RL by interpreting reward parameters as coordinates on a task manifold. We show that, by minimizing the excess thermodynamic work, optimal curricula correspond to geodesics in this task space. As […]

Ver mais

Hi , I’m much interested into applied RL and looking for a job or a summer internship this summer , I’m a 3rd year undergrad at a tier 1 research institute . However my doubt is my main interest in rl is its ability to create greater impact , speaking about impact what I truly wanted was to use sample efficient rl and create an impact in sustainability and energy grid optimization but I think a greater application […]

Ver mais

The resummation of superfactorially divergent series represents a significant computational challenge in mathematical physics. In the present paper the resummation of a specific class of Stieltjes series characterized by a moment sequence growing as $(2n)!$ will be addressed. Despite the fact that Carleman’s condition is satisfied for these series, the practical utility of Padé approximants in resumming them is severely compromised by an extremely slow convergence rate. Weniger’s $delta$-transformation is proposed as a superior resummation tool. Some recently […]

Ver mais

The dynamics of gradient-based training in neural networks often exhibit nontrivial structures; hence, understanding them remains a central challenge in theoretical machine learning. In particular, a concept of feature unlearning, in which a neural network progressively loses previously learned features over long training, has gained attention. In this study, we consider the infinite-width limit of a two-layer neural network updated with a large-batch stochastic gradient, then derive differential equations with different time scales, revealing the mechanism and conditions […]

Ver mais