English
Related papers

Related papers: Entropy Collapse: A Universal Failure Mode of Inte…

200 papers

Transferring knowledge from one neural network to another has been shown to be helpful for learning tasks with few training examples. Prevailing fine-tuning methods could potentially contaminate pre-trained features by comparably high…

Machine Learning · Computer Science 2019-07-15 Farshid Varno , Behrouz Haji Soleimani , Marzie Saghayi , Lisa Di Jorio , Stan Matwin

As the variety of systems displaying scale invariant characteristics are matched only by their number, it is becoming increasingly important to understand their fundamental and universal elements. Much work has attempted to apply 2nd order…

Statistical Mechanics · Physics 2023-12-18 Ronaldo Ortez , John B. Rundle

Test-Time Adaptation (TTA) enhances model robustness to out-of-distribution (OOD) data by updating the model online during inference, yet existing methods lack theoretical insights into the fundamental causes of performance degradation…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Xiao Chen , Zhongjing Du , Jiazhen Huang , Xu Jiang , Li Lu , Jingyan Jiang , Zhi Wang

The entanglement entropy (EE) of quantum systems is often used as a test of low-energy descriptions by conformal field theory (CFT). Here we point out that this is not a reliable indicator, as the EE often shows the same behavior even when…

Strongly Correlated Electrons · Physics 2017-08-02 Pranay Patil , Ying Tang , Emanuel Katz , Anders W. Sandvik

Weak multiplex percolation generalizes percolation to multi-layer networks, represented as networks with a common set of nodes linked by multiple types (colors) of edges. We report a novel discontinuous phase transition in this problem.…

Physics and Society · Physics 2022-03-15 R. A. da Costa , G. J. Baxter , S. N. Dorogovtsev , J. F. F. Mendes

Recent years have witnessed the huge success of deep neural networks (DNNs) in various tasks of computer vision and text processing. Interestingly, these DNNs with massive number of parameters share similar structural properties on their…

Machine Learning · Statistics 2023-10-26 Wanli Hong , Shuyang Ling

The training algorithms for AI systems all introduce far-from-equilibrium dynamical processes, and understanding the irreversibility of these algorithms is a fundamental step towards understanding the learning dynamics of modern AI systems.…

Statistical Mechanics · Physics 2026-05-22 Liu Ziyin , Yuanjie Ren , Adam Levine , Isaac Chuang

The entanglement entropy of a subsystem $A$ of a quantum system is expressed, in the replica method, through analytic continuation with respect to n of the trace of the n-th power of the reduced density matrix $\tr\rho_A^n$. We study the…

Statistical Mechanics · Physics 2010-03-25 F. Gliozzi , L. Tagliacozzo

When deploying artificial agents in real-world environments where they interact with humans, it is crucial that their behavior is aligned with the values, social norms or other requirements of that environment. However, many environments…

Machine Learning · Computer Science 2023-05-05 Mattijs Baert , Pietro Mazzaglia , Sam Leroux , Pieter Simoens

Via extensive Monte Carlo simulations along with systematic analyses of corrections to scaling, we estimate the order parameter critical exponent $\beta$ of absorbing phase transitions in systems with two symmetric absorbing states. The…

Statistical Mechanics · Physics 2020-05-18 Su-Chan Park

We observe a novel 'multiple-descent' phenomenon during the training process of LSTM, in which the test loss goes through long cycles of up and down trend multiple times after the model is overtrained. By carrying out asymptotic stability…

Machine Learning · Computer Science 2025-05-27 Wenbo Wei , Nicholas Chong Jia Le , Choy Heng Lai , Ling Feng

We study fidelity and fidelity susceptibility by addition of entanglement of entropy in the one-dimensional quantum compass model in a transverse magnetic field numerically. The whole four recognized gapped regions in the ground state phase…

Strongly Correlated Electrons · Physics 2014-06-13 Mostafa Motamedifar , Somayyeh Nemati , Saeed Mahdavifar , Saber Farjami Shayesteh

Grokking - the delayed transition from memorisation to generalisation in neural networks - remains poorly understood. We study this phenomenon through the geometry of learned representations and identify a consistent empirical signature…

Machine Learning · Computer Science 2026-05-13 Truong Xuan Khanh , Truong Quynh Hoa , Luu Duc Trung , Phan Thanh Duc

Standard Transformers have a fixed computational depth, fundamentally limiting their ability to generalize to tasks requiring variable-depth reasoning, such as multi-hop graph traversal or nested logic. We propose a depth-recurrent…

Machine Learning · Computer Science 2026-03-24 Hung-Hsuan Chen

When instructed to underperform on multiple-choice evaluations, do language models engage with question content or fall back on positional shortcuts? We map the boundary between these regimes using a six-condition adversarial…

Computation and Language · Computer Science 2026-05-01 Jon-Paul Cacioli

Uncovering and understanding universal dynamics in matter far from equilibrium remains a key challenge. In this work, we identify a so far unrecognized form of universal behavior that emerges after a sudden symmetry-breaking quench at…

Quantum Physics · Physics 2026-05-11 Tobias Wiener , Laurin Brunner , Markus Heyl

Deploying reinforcement learning in safety critical domains, from autonomous vehicles to medical decision support, is constrained by failures arising when systems encounter unfamiliar conditions. We argue that the fundamental bottleneck is…

Systems and Control · Electrical Eng. & Systems 2026-05-27 Chayan Banerjee , Ethan Goan

Reinforcement learning with verifiable rewards (RLVR) has emerged as a prominent paradigm for enhancing the reasoning capabilities of large language models (LLMs). However, the entropy of LLMs usually collapses during RLVR training, leading…

Computation and Language · Computer Science 2026-04-21 Renren Jin , Pengzhi Gao , Yuqi Ren , Zhuowen Han , Tongxuan Zhang , Wuwei Huang , Wei Liu , Jian Luan , Deyi Xiong

The deployment of machine learning in high-stakes services relies on ``human-in-the-loop'' architectures to mitigate algorithmic uncertainty. However, existing static policies fail to address a fundamental tension: algorithms suffer from…

Optimization and Control · Mathematics 2026-02-02 Ziyao Wang , Svetlozar T Rachev

We examine the temporal evolution of the modular entropy and capacity (in particular, the fluctuation of the entanglement entropy) for systems of time-dependent oscillators coupled by a (time-dependent) parameter. Such models, through the…

High Energy Physics - Theory · Physics 2023-12-25 K. Andrzejewski