English
Related papers

Related papers: Sharp Spectral Thresholds for Logit Fixed Points

200 papers

Estimating model accuracy on unseen, unlabeled datasets is crucial for real-world machine learning applications, especially under distribution shifts that can degrade performance. Existing methods often rely on predicted class probabilities…

Machine Learning · Computer Science 2025-08-28 Chenzhi Liu , Mahsa Baktashmotlagh , Yanran Tang , Zi Huang , Ruihong Qiu

This paper deals with the stabilization of a class of linear infinite-dimensional systems with unbounded control operators and subject to a boundary disturbance. We assume that there exists a linear feedback law that makes the origin of the…

Analysis of PDEs · Mathematics 2022-10-26 Ismaïla Balogoun , Swann Marx , Franck Plestan

This paper addresses the problem of robust dynamic output stabilization of FO-LTI interval systems with the fractional order 0<{\alpha}<2, in terms of linear matrix inequalities (LMIs). Our purpose is to design a robust dynamic output…

Systems and Control · Computer Science 2018-07-31 Pouya Badri , Mahdi Sojoodi

Enabling machine learning classifiers to defer their decision to a downstream expert when the expert is more accurate will ensure improved safety and performance. This objective can be achieved with the learning-to-defer framework which…

Machine Learning · Computer Science 2023-11-03 Yuzhou Cao , Hussein Mozannar , Lei Feng , Hongxin Wei , Bo An

Understanding the intricate non-convex training dynamics of softmax-based models is crucial for explaining the empirical success of transformers. In this article, we analyze the gradient flow dynamics of the value-softmax model, defined as…

Machine Learning · Computer Science 2026-03-09 Aditya Varre , Mark Rofin , Nicolas Flammarion

Optimization analyses for cross-entropy training rely on local Taylor models of the loss to predict whether a proposed step will decrease the objective. These surrogates are reliable only inside the Taylor convergence radius of the true…

Machine Learning · Computer Science 2026-03-17 Piyush Sao

The local eigenvalue statistics of large random matrices near a hard edge transitioning into a soft edge are described by the Bessel process associated with a large parameter $\alpha$. For this point process, we obtain 1) exponential moment…

Probability · Mathematics 2021-04-26 Christophe Charlier , Jonatan Lenells

We establish sharp well-posedness and approximation estimates for variational saddle point systems at the continuous level. The main results of this note have been known to be true only in the finite dimensional case. Known spectral results…

Numerical Analysis · Mathematics 2014-11-04 Constantin Bacuta

High-confidence errors in large language models are often treated as fragile failures. We study an alternative: some errors may be false fixed points, locally stable, internally coherent, and confidently wrong. This separates robustness…

Artificial Intelligence · Computer Science 2026-05-26 Akira Okutomi

In mechanistic interpretability, recent work scrutinizes transformer "circuits" - sparse, mono or multi layer sub computations, that may reflect human understandable functions. Yet, these network circuits are rarely acid-tested for their…

Machine Learning · Computer Science 2026-02-20 Karan Bali , Jack Stanley , Praneet Suresh , Danilo Bzdok

We develop a predictor-feedback control design for multi-input nonlinear systems with distinct input delays, of arbitrary length, in each individual input channel. Due to the fact that different input signals reach the plant at different…

Optimization and Control · Mathematics 2015-08-25 Nikolaos Bekiaris-Liberis , Miroslav Krstic

This paper deals with the problem of robust dynamic output feedback stabilization of interval fractional-order linear time invariant (FO-LTI) systems with the fractional order $1\le\alpha<2$. In this study, a new formulation based on the…

Systems and Control · Electrical Eng. & Systems 2020-04-02 Pouya Badri , Mahdi Sojoodi

The principal task to control dynamical systems is to ensure their stability. When the system is unknown, robust approaches are promising since they aim to stabilize a large set of plausible systems simultaneously. We study linear…

Systems and Control · Electrical Eng. & Systems 2020-11-24 Lenart Treven , Sebastian Curi , Mojmir Mutny , Andreas Krause

This paper is devoted to the development of adaptive control schemes for uncertain discrete-time systems, which guarantee robust, global, exponential convergence to the desired equilibrium point of the system. The proposed control scheme…

Optimization and Control · Mathematics 2015-09-02 Iasson Karafyllis , Maria Kontorinaki , Markos Papageorgiou

We consider the linear stability problem for a 3D cylindrically symmetric equilibrium of the relativistic Vlasov-Maxwell system that describes a collisionless plasma. For an equilibrium whose distribution function decreases monotonically…

Plasma Physics · Physics 2009-11-13 Zhiwu Lin , Walter Strauss

We introduce a new discrete-time attention model, termed the localmax dynamics, which interpolates between the classic softmax dynamics and the hardmax dynamics, where only the tokens that maximize the influence toward a given token have a…

Computation and Language · Computer Science 2025-09-22 Henri Cimetière , Maria Teresa Chiri , Bahman Gharesifard

We examine robust output feedback control of discrete-time nonlinear systems with bounded uncertainties affecting the dynamics and measurements. Specifically, we demonstrate how to construct semi-infinite programs that produce gains to…

Systems and Control · Electrical Eng. & Systems 2024-09-16 Jad Wehbeh , Eric C. Kerrigan

Stochastic feedback systems give rise to a variety of notions of stability. The conditions for the stability of the median, mean, and variance stability conditions differ. These conditions can be stated explicitly for scalar discrete-time…

Systems and Control · Electrical Eng. & Systems 2019-12-19 Roy S. Smith , Bassam Bamieh

Fine-tuning pretrained language models can improve task performance while subtly altering the evidence a model relies on. We propose a training-time interpretability view that tracks token-level attributions across finetuning epochs. We…

Artificial Intelligence · Computer Science 2026-01-21 Sahil Rajesh Dhayalkar

This paper addresses the following question: "Suppose that a state-feedback controller stabilizes an infinite-dimensional linear continuous-time system. If we choose the parameters of an event/self-triggering mechanism appropriately, is the…

Optimization and Control · Mathematics 2022-07-05 Masashi Wakaiki , Hideki Sano