English
Related papers

Related papers: Autoencoder-assisted study of directed percolation…

200 papers

This review addresses recent developments in nonequilibrium statistical physics. Focusing on phase transitions from fluctuating phases into absorbing states, the universality class of directed percolation is investigated in detail. The…

Statistical Mechanics · Physics 2015-06-24 Haye Hinrichsen

Variational Autoencoders (VAEs) are well-established as a principled approach to probabilistic unsupervised learning with neural networks. Typically, an encoder network defines the parameters of a Gaussian distributed latent space from…

Machine Learning · Computer Science 2025-05-16 Alan Jeffares , Liyuan Liu

The contractive auto-encoder learns a representation of the input data that captures the local manifold structure around each data point, through the leading singular vectors of the Jacobian of the transformation from input to…

Machine Learning · Computer Science 2012-07-03 Salah Rifai , Yoshua Bengio , Yann Dauphin , Pascal Vincent

Throughout developmental biology and ecology, transport can be driven by nonlocal interactions. Examples include cells that migrate based on contact with pseudopodia extended from other cells, and animals that move based on their vision of…

Pattern Formation and Solitons · Physics 2023-07-07 Thomas Jun Jewell , Andrew L. Krause , Philip K. Maini , Eamonn A. Gaffney

Stochastic processes have found numerous applications in science, as they are broadly used to model a variety of natural phenomena. Due to their intrinsic randomness and uncertainty, they are, however, difficult to characterize. Here, we…

Conventional approaches for simulating steady-state distributions of particles under diffusive and advective transport at high P\'eclet numbers involve solving the diffusion and advection equations in at least two dimensions. Here, we…

Pedestrian trajectory forecasting is a fundamental task in multiple utility areas, such as self-driving, autonomous robots, and surveillance systems. The future trajectory forecasting is multi-modal, influenced by physical interaction with…

Computer Vision and Pattern Recognition · Computer Science 2022-02-09 Jiashi Gao , Xinming Shi , James J. Q. Yu

We introduce and solve a model of hardcore particles on a one dimensional periodic lattice which undergoes an active-absorbing state phase transition at finite density. In this model an occupied site is defined to be active if its left…

Statistical Mechanics · Physics 2009-07-28 Urna Basu , P. K. Mohanty

Reinforcement learning provides a powerful and flexible framework for automated acquisition of robotic motion skills. However, applying reinforcement learning requires a sufficiently detailed representation of the state, including the…

Machine Learning · Computer Science 2016-03-02 Chelsea Finn , Xin Yu Tan , Yan Duan , Trevor Darrell , Sergey Levine , Pieter Abbeel

This paper introduces an efficient and robust method for discovering interpretable circuits in large language models using discrete sparse autoencoders. Our approach addresses key limitations of existing techniques, namely computational…

Computation and Language · Computer Science 2024-05-22 Charles O'Neill , Thang Bui

Molecular dynamics simulations produce data with complex nonlinear dynamics. If the timestep behavior of such a dynamic system can be represented by a linear operator, future states can be inferred directly without expensive simulations.…

Machine Learning · Computer Science 2021-05-27 Willis Hoke , Daniel Shea , Stephen Casey

Addressing the charged particle beam diagnostics in accelerators poses a formidable challenge, demanding high-fidelity simulations in limited computational time. Machine learning (ML) based surrogate models have emerged as a promising tool…

Accelerator Physics · Physics 2024-08-09 Mahindra Rautela , Alan Williams , Alexander Scheinker

Classic variational autoencoders are used to learn complex data distributions, that are built on standard function approximators. Especially, VAE has shown promise on a lot of complex task. In this paper, a new autoencoder model -…

Computer Vision and Pattern Recognition · Computer Science 2020-01-13 Qiuyu Zhu , Ruixin Zhang

A disentangled representation of a data set should be capable of recovering the underlying factors that generated it. One question that arises is whether using Euclidean space for latent variable models can produce a disentangled…

Machine Learning · Computer Science 2020-03-23 Luis A. Pérez Rey

We present a variational autoencoder framework for learning and generating configurations of structured polymer globules from distance matrices. We used coarse-grained molecular dynamics to sample polyethylene structures, which we used as…

Error-bounded lossy compression is becoming an indispensable technique for the success of today's scientific projects with vast volumes of data produced during simulations or instrument data acquisitions. Not only can it significantly…

Machine Learning · Computer Science 2023-10-24 Jinyang Liu , Sheng Di , Kai Zhao , Sian Jin , Dingwen Tao , Xin Liang , Zizhong Chen , Franck Cappello

A monomer-dimer reaction lattice model with lateral repulsion among the same species is studied using a mean-field analysis and Monte Carlo simulations. For weak repulsions, the model exhibits a first-order irreversible phase transition…

Statistical Mechanics · Physics 2009-10-30 Roberto A. Monetti

It is argued that some phase--transitions observed in models of non-equilibrium wetting phenomena are related to contact processes with long-range interactions. This is investigated by introducing a model where the activation rate of a site…

Statistical Mechanics · Physics 2009-11-10 F. Ginelli , H. Hinrichsen , R. Livi , D. Mukamel , A. Politi

Formal verification provides a powerful framework for proving that dynamical systems satisfy their specifications. However, these techniques face scalability challenges in high-dimensional settings, as they often rely on state-space…

Machine Learning · Computer Science 2026-05-21 Robert Reed , Luca Laurenti , Morteza Lahijanian

Deep generative models have been enjoying success in modeling continuous data. However it remains challenging to capture the representations for discrete structures with formal grammars and semantics, e.g., computer programs and molecular…

Machine Learning · Computer Science 2018-02-27 Hanjun Dai , Yingtao Tian , Bo Dai , Steven Skiena , Le Song