English
Related papers

Related papers: Avoiding Premature Collapse: Adaptive Annealing fo…

200 papers

Deploying continual object detection on microcontrollers (MCUs) with under 100KB memory requires efficient feature compression that can adapt to evolving task distributions. Existing approaches rely on fixed compression strategies (e.g.,…

Artificial Intelligence · Computer Science 2026-04-14 Bibin Wilson

A foundational assumption in complex-system collapse studies is that critical transitions are second-order, preceded by early-warning signals like rising autocorrelation, variance, and critical slowing down (Scheffer, 2009). We show this…

Artificial Intelligence · Computer Science 2026-03-17 Truong Xuan Khanh , Truong Quynh Hoa

Supervised Fine-Tuning (SFT) is the standard paradigm for domain adaptation, yet it frequently incurs the cost of catastrophic forgetting. In sharp contrast, on-policy Reinforcement Learning (RL) effectively preserves general capabilities.…

Machine Learning · Computer Science 2026-01-06 Muxi Diao , Lele Yang , Wuxuan Gong , Yutong Zhang , Zhonghao Yan , Yufei Han , Kongming Liang , Weiran Xu , Zhanyu Ma

Test-time adaptation aims to adapt to realistic environments in an online manner by learning during test time. Entropy minimization has emerged as a principal strategy for test-time adaptation due to its efficiency and adaptability.…

Computer Vision and Pattern Recognition · Computer Science 2025-05-23 Jisu Han , Jaemin Na , Wonjun Hwang

Anomaly detection in complex dynamical systems is essential for ensuring reliability, safety, and efficiency in industrial and cyber-physical infrastructures. Predictive maintenance helps prevent costly failures, while cybersecurity…

Machine Learning · Computer Science 2025-09-25 Michael Somma , Thomas Gallien , Branka Stojanovic

Despite their success, large pretrained vision models remain vulnerable to catastrophic forgetting when adapted to new tasks in class-incremental settings. Parameter-efficient fine-tuning (PEFT) alleviates this by restricting trainable…

Machine Learning · Computer Science 2026-02-17 Yaqian Zhang , Bernhard Pfahringer , Eibe Frank , Albert Bifet

The steepest-entropy-ascent quantum thermodynamic (SEAQT) framework was used to calculate the stability of a collection of point defects in 2D PtSe$_2$ and predict the kinetics with which defects rearrange during thermal annealing. The…

Materials Science · Physics 2022-12-19 Aimen Younis , Fazel Baniasadi , Michael R. von Spakovsky , William T. Reynolds

Proactive autoscaling for containerized workloads depends on knowing the provisioning delay, i.e., the time between a scaling decision and the moment new capacity is ready to serve traffic. In practice, this cold-start duration can vary…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-18 Himanshu Singh Baghel

Training stability is of great importance to Transformers. In this work, we investigate the training dynamics of Transformers by examining the evolution of the attention layers. In particular, we track the attention entropy for each…

It is known in \cite{beccari} that the standard explicit Euler-type scheme (such as the exponential Euler and the linear-implicit Euler schemes) with a uniform timestep, though computationally efficient, may diverge for the stochastic…

Numerical Analysis · Mathematics 2023-11-14 Chuchu Chen , Tonghe Dang , Jialin Hong

Learning performed over finite time is inherently irreversible. In Part~I of this series, we modeled learning as a transport process in the space of parameter distributions and derived the Epistemic Speed Limit (ESL), which lower-bounds…

Machine Learning · Computer Science 2026-02-12 Daisuke Okanohara

Unsupervised anomaly detection (AD) methods typically assume clean training data, yet real-world datasets often contain undetected or mislabeled anomalies, leading to significant performance degradation. Existing solutions require access to…

Machine Learning · Computer Science 2026-01-30 Sukanya Patra , Souhaib Ben Taieb

This work proposes a new adaptive-robust control (ARC) architecture for a class of uncertain Euler-Lagrange (EL) systems where the upper bound of the uncertainty satisfies linear in parameters (LIP) structure. Conventional ARC strategies…

Systems and Control · Computer Science 2018-05-10 Spandan Roy , Sayan Basu Roy , Indra Narayan Kar

In this paper, we propose an accelerated version for the Sinkhorn algorithm, which is the reference method for computing the solution to Entropic Optimal Transport. Its main draw-back is the exponential slow-down of convergence as the…

Numerical Analysis · Mathematics 2025-06-19 Reda Chhaibi , Serge Gratton , Samuel Vaiter

A novel method of exponentially stable adaptive control to compensate for matched parametric uncertainty under a mild condition of semi-persistent excitation (s-PE) of a regressor with piecewise-constant rank and nullspace is proposed. It…

Systems and Control · Electrical Eng. & Systems 2022-10-24 Anton Glushchenko , Konstantin Lastochkin

In this paper we apply the formalism of translation invariant (continuous) matrix product states in the thermodynamic limit to $(1+1)$ dimensional critical models. Finite bond dimension bounds the entanglement entropy and introduces an…

Quantum Physics · Physics 2015-06-18 Vid Stojevic , Jutho Haegeman , I. P. McCulloch , L. Tagliacozzo , Frank Verstraete

This paper presents extensions of finite-time stability results to some prototypical adaptive control and estimation frameworks. First, we present a novel scheme of online parameter estimation that guarantees convergence of the estimation…

Optimization and Control · Mathematics 2020-10-20 Kunal Garg , Parag Bobade , Dimitra Panagou

Cyberattacks on critical infrastructure, particularly water distribution systems, have increased due to rapid digitalization and the integration of IoT devices and industrial control systems (ICS). These cyber-physical systems (CPS)…

Cryptography and Security · Computer Science 2025-09-22 Michael Somma

Continual learning aims to incrementally acquire new concepts in data streams while resisting forgetting previous knowledge. With the rise of powerful pre-trained models (PTMs), there is a growing interest in training incremental learning…

Machine Learning · Computer Science 2024-11-05 Linglan Zhao , Xuerui Zhang , Ke Yan , Shouhong Ding , Weiran Huang

Real-world reinforcement learning often faces environment drift, but most existing methods rely on static entropy coefficients/target entropy, causing over-exploration during stable periods and under-exploration after drift, and leaving…

Machine Learning · Computer Science 2026-05-19 Tongxi Wang , Zhuoyang Xia , Xinran Chen , Shan Liu
‹ Prev 1 2 3 10 Next ›