arXiv subjects

Yihang Wang

Publications and source records attributed to Yihang Wang.

28 records · Page 2Linked to original sources

arXiv2024

From latent dynamics to meaningful representations

While representation learning has been central to the rise of machine learning and artificial intelligence, a key problem remains in making the learned representations meaningful. For this, the typical approach is to regularize the learned representation through prior probability distributions. However, such priors are usually unavailable or are ad hoc. To deal with this, recent efforts have shifted towards leveraging the insights from physical principles to guide the learning process. In this spirit, we propose a purely dynamics-constrained representation learning framework. Instead of relying on predefined probabilities, we restrict the latent representation to follow overdamped Langevin dynamics with a learnable transition density - a prior driven by statistical mechanics. We show this is a more natural constraint for representation learning in stochastic dynamical systems, with the crucial ability to uniquely identify the ground truth representation. We validate our framework for different systems including a real-world fluorescent DNA movie dataset. We show that our algorithm can uniquely identify orthogonal, isometric and meaningful latent representations.

cs.LG↗

arXiv2024

Token-Efficient Leverage Learning in Large Language Models

Large Language Models (LLMs) have excelled in various tasks but perform better in high-resource scenarios, which presents challenges in low-resource scenarios. Data scarcity and the inherent difficulty of adapting LLMs to specific tasks compound the challenge. To address the twin hurdles, we introduce \textbf{Leverage Learning}. We present a streamlined implement of this methodology called Token-Efficient Leverage Learning (TELL). TELL showcases the potential of Leverage Learning, demonstrating effectiveness across various LLMs and low-resource tasks, ranging from $10^4$ to $10^6$ tokens. It reduces task data requirements by up to nearly an order of magnitude compared to conventional Supervised Fine-Tuning (SFT) while delivering competitive performance. With the same amount of task data, TELL leads in improving task performance compared to SFT. We discuss the mechanism of Leverage Learning, suggesting it aligns with quantization hypothesis and explore its promising potential through empirical testing.

cs.CL↗

arXiv2022

Predicted Trajectory Guidance Control Framework of Teleoperated Ground Vehicles Compensating for Delays

Maneuverability and drivability of the teleoperated ground vehicle could be seriously degraded by large communication delays if the delays are not properly compensated. This paper proposes a predicted trajectory guidance control (PTGC) framework to compensate for such delays, thereby improving the performance of the teleoperation system. The novelty of this PTGC framework is that teleoperators intended trajectory is predicted at the vehicle side with their delayed historical control commands and the LiDAR 3D point cloud of the environment, and then the vehicle is guided by the predicted trajectory. By removing the teleoperator from the direct control loop, the presented method is less sensitive to delays, and delays are compensated as long as the prediction horizon exceeds the delays. Human-in-the-loop simulation experiments are designed to evaluate the teleoperation performance with the proposed method under five delay levels. Based on the repeated measurement analysis of variance, it is concluded that the PTGC method can significantly improve the performance of the teleoperated ground vehicles under large delays(>200ms), such as the task completion time (TCT), deviation to centerline (D2C) and steering effort (SE). In addition, the results also show that teleoperators can adapt to smaller delays, and the presented method is ineffective in such cases.

eess.SY↗

arXiv2022

From data to noise to data: mixing physics across temperatures with generative artificial intelligence

Using simulations or experiments performed at some set of temperatures to learn about the physics or chemistry at some other arbitrary temperature is a problem of immense practical and theoretical relevance. Here we develop a framework based on statistical mechanics and generative Artificial Intelligence that allows solving this problem. Specifically, we work with denoising diffusion probabilistic models, and show how these models in combination with replica exchange molecular dynamics achieve superior sampling of the biomolecular energy landscape at temperatures that were never even simulated without assuming any particular slow degrees of freedom. The key idea is to treat the temperature as a fluctuating random variable and not a control parameter as is usually done. This allows us to directly sample from the joint probability distribution in configuration and temperature space. The results here are demonstrated for a chirally symmetric peptide and single-strand ribonucleic acid undergoing conformational transitions in all-atom water. We demonstrate how we can discover transition states and metastable states that were previously unseen at the temperature of interest, and even bypass the need to perform further simulations for wide range of temperatures. At the same time, any unphysical states are easily identifiable through very low Boltzmann weights. The procedure while shown here for a class of molecular simulations should be more generally applicable to mixing information across simulations and experiments with varying control parameters.

cond-mat.stat-mech↗

arXiv2020

Understanding the role of predictive time delay and biased propagator in RAVE

In this work, we revisit our recent iterative machine learning (ML) -- molecular dynamics (MD) technique "Reweighted autoencoded variational Bayes for enhanced sampling (RAVE)" (Ribeiro, Bravo, Wang, Tiwary, J. Chem. Phys. 149 072301 (2018) and Wang, Ribeiro, Tiwary, Nature Commun. 10 3573 (2019)) and analyze as well as formalize some of its approximations. These including: (a) the choice of a predictive time-delay, or how far into the future should the ML try to predict the state of a given system output from MD, and (b) for short time-delays, how much of an error is made in approximating the biased propagator for the dynamics as the unbiased propagator. We demonstrate through a master equation framework as to why the exact choice of time-delay is irrelevant as long as a small non-zero value is adopted. We also derive a correction to reweight the biased propagator, and somewhat to our dissatisfaction but also to our reassurance, find that it barely makes a difference to the intuitive picture we had previously derived and used.

cond-mat.stat-mech↗

arXiv2019

Machine learning approaches for analyzing and enhancing molecular dynamics simulations

Molecular dynamics (MD) has become a powerful tool for studying biophysical systems, due to increasing computational power and availability of software. Although MD has made many contributions to better understanding these complex biophysical systems, there remain methodological difficulties to be surmounted. First, how to make the deluge of data generated in running even a microsecond long MD simulation human comprehensible. Second, how to efficiently sample the underlying free energy surface and kinetics. In this short perspective, we summarize machine learning based ideas that are solving both of these limitations, with a focus on their key theoretical underpinnings and remaining challenges.

physics.comp-ph↗

arXiv2018

Ligand dissociation mechanisms from all-atom simulations: Are we there yet?

Large parallel gains in the development of both computational resources as well as sampling methods have now made it possible to simulate dissociation events in ligand-protein complexes with all--atom resolution. Such encouraging progress, together with the inherent spatiotemporal resolution associated with molecular simulations, has left their use for investigating dissociation processes brimming with potential, both in rational drug design, where it can be an invaluable tool for determining the mechanistic driving forces behind dissociation rate constants, as well as in force-field development, where it can provide a catalog of transient molecular structures on which to refine force-fields. Although much progress has been made in making force-fields more accurate, reducing their error for transient structures along a transition path could yet prove to be a critical development helping to make kinetic predictions much more accurate. In what follows we will provide a state-of-the-art compilation of the molecular dynamics (MD) methods used to investigate the kinetics and mechanisms of ligand-protein dissociation processes. Due to the timescales of such processes being slower than what is accessible using straightforward MD simulations, several ingenious schemes are being devised at a rapid rate to overcome this obstacle. Here we provide an up-to-date compendium of such methods and their achievements/shortcomings in extracting mechanistic insight into ligand-protein dissociation. We conclude with a critical and provocative appraisal attempting to answer the title of this review.

physics.bio-ph↗

arXiv2018

Reweighted Autoencoded Variational Bayes for Enhanced Sampling (RAVE)

Here we propose the Reweighted Autoencoded Variational Bayes for Enhanced Sampling (RAVE) method, a new iterative scheme that uses the deep learning framework of variational autoencoders to enhance sampling in molecular simulations. RAVE involves iterations between molecular simulations and deep learning in order to produce an increasingly accurate probability distribution along a low-dimensional latent space that captures the key features of the molecular simulation trajectory. Using the Kullback-Leibler divergence between this latent space distribution and the distribution of various trial reaction coordinates sampled from the molecular simulation, RAVE determines an optimum, yet nonetheless physically interpretable, reaction coordinate and optimum probability distribution. Both then directly serve as the biasing protocol for a new biased simulation, which is once again fed into the deep learning module with appropriate weights accounting for the bias, the procedure continuing until estimates of desirable thermodynamic observables are converged. Unlike recent methods using deep learning for enhanced sampling purposes, RAVE stands out in that (a) it naturally produces a physically interpretable reaction coordinate, (b) is independent of existing enhanced sampling protocols to enhance the fluctuations along the latent space identified via deep learning, and (c) it provides the ability to easily filter out spurious solutions learned by the deep learning procedure. The usefulness and reliability of RAVE is demonstrated by applying it to model potentials of increasing complexity, including computation of the binding free energy profile for a hydrophobic ligand-substrate system in explicit water with dissociation time of more than three minutes, in computer time at least twenty times less than that needed for umbrella sampling or metadynamics.

physics.chem-ph↗

arXiv2017

The computation of strain rate tensor in multiple-relaxation-time lattice Boltzmann model

Multiple-relaxation-time (MRT) lattice Boltzmann (LB) model is an important class of LB model with lots of advantages over traditional single-relaxation-time (SRT) LB model. In addition, the computation of strain rate tensor is crucial in MRT-LB simulations of some complex flows. Up to now, there are only two formulas to compute the strain rate tensor in the MRT LB model. One is to compute the strain rate tensor by using non-equilibrium parts of macroscopic moments (Yu formula). The other is to compute the strain rate tensor by using non-equilibrium parts of density distribution functions (Chai formula). The mathematical expressions of these two formulas are so different that we do not know which formula to choose for computing the strain rate tensor in MRT LB model. In this paper, we study the relationship of these two formulas. It is found that Yu formula can be deduced from Chai formula in a particular procedure. However, these two formulas have their own advantages and disadvantages. Yu formula is more efficient in the computation aspect while Chai formula can be applied to more lattice patterns of MRT LB models. It is also found that deducing Yu formula for a particular lattice pattern from Chai formula is more convenient than the way proposed by Yu et al.

physics.flu-dyn↗

arXiv2015

14-velocity and 18-velocity multiple-relaxation-time lattice Boltzmann models for three-dimensional incompressible flows

In this paper, 14-velocity and 18-velocity multiple-relaxation-time (MRT) lattice Boltzmann (LB) models are proposed for three-dimensional incompressible flows. These two models are constructed based on the incompressible LBGK model proposed by He et al. (Chin. Phys., 2004, 13: 40-46) and the MRT LB model proposed by d'Humières et al. (Philos. Trans. R. Soc., A, 2002, 360: 437-451), which have advantages in the computational efficiency and stability, respectively. Through the Chapman-Enskog analysis, the models can recover to three-dimensional incompressible Navier-Stokes equations in the low Mach number limit. To verify the present models, the steady Poiseuille flow, unsteady pulsatile flow and lid-driven cavity flow in three dimensions are simulated. The simulation results agree well with the analytical solutions or the existing numerical results. Moreover, it is found that the present models show higher accuracy than d'Humières et al. model and better stability than He et al. model.

physics.flu-dyn↗