arXiv research

Gradient model for memristive systems in neurophysiology and neuromorphic circuits.

Estimates heat kernel gradients on fractal-like cable systems.

Faster policy learning via continuous-time gradients.

The article reviews how gradient flow systems on hypergraphs connect to information geometry and nonequilibrium physics.

New loss function helps learn unstable dynamical systems.

We investigate necessary and sufficient conditions under which a general nonlinear affine control system with outputs can be written as a gradient control system corresponding to some pseudo-Riemannian metric defined on the state space. The results rely on a suitable notion of compatibility of the system with respect t…

This paper proposes a novel PGO framework to optimize systemic risk bailouts using neural networks.

The paper studies a gradient system on a beta statistical manifold, proving integrability and deriving explicit expressions.

Reinforcement learning is a promising approach to learning robotics controllers. It has recently been shown that algorithms based on finite-difference estimates of the policy gradient are competitive with algorithms based on the policy gradient theorem. We propose a theoretical framework for understanding this phenomen…

Gradient descent optimization improved by circuit perspective.

Improved sampling efficiency for molecular systems using path gradients after Flow Matching.

This work develops a particle system to approximate Fisher-Rao gradient flows in mean-field optimization.

Estimates log-likelihood of interacting particle systems using virtual particles.

We consider gradient Ricci solitons conformal to a $n$-dimensional pseudo-Euclidean space and we completely describe the most general ansatz that reduces the resulting system of partial differential equations to a system of ordinary differential equations. As a consequence, the gradient Ricci solitons that arise from t…

StarNet trains deep models without gradients using linear equations.

The article derives gradient estimations for semilinear equations on geometric flows.

New method for identifying autoregressive systems on manifolds.

The paper speeds up hyperparameter optimisation in Gaussian processes.

Natural gradient simplification for deep learning networks.

A distributed system identification method for LTI systems using reverse experience replay.

The complete invariant for gradient like Morse-Smale dynamical systems (vector fields and diffeomorphisms) on closed 4-manifolds are constructed. It is same as Kirby diagram in a case of polar vector field without fixed points of index 3.

LEM efficiently models long-term sequences with gradients.

A new Adamize method improves multi-objective recommender systems.

Takagi-Sugeno-Kang (TSK) fuzzy systems are very useful machine learning models for regression problems. However, to our knowledge, there has not existed an efficient and effective training algorithm that ensures their generalization performance, and also enables them to deal with big data. Inspired by the connections b…

Policy gradient converges to globally optimal policy in nearly linear-quadratic systems.

We prove that stochastic gradient descent efficiently converges to the global optimizer of the maximum likelihood objective of an unknown linear time-invariant dynamical system from a sequence of noisy observations generated by the system. Even though the objective function is non-convex, we provide polynomial running …

Paper proposes new gradient codes for robust distributed machine learning.

We use differential equations based approaches to provide some {\it \textbf{physics}} insights into analyzing the dynamics of popular optimization algorithms in machine learning. In particular, we study gradient descent, proximal gradient descent, coordinate gradient descent, proximal coordinate gradient, and Newton's …

The paper examines partial regularity of Lipschitz solutions to minimal surface system.

Paper introduces a new adaptive gradient method with gradient compression for distributed training.

This paper studies how gradient descent in control systems can perform well on unseen data.

The extended Kalman filter is perhaps the most standard tool to estimate in real time the state of a dynamical system from noisy measurements of some function of the system, with extensive practical applications (such as position tracking via GPS). While the plain Kalman filter for linear systems is well-understood, th…

New method learns nonlinear systems from single finite trajectory samples.

Recommender systems need to mirror the complexity of the environment they are applied in. The more we know about what might benefit the user, the more objectives the recommender system has. In addition there may be multiple stakeholders - sellers, buyers, shareholders - in addition to legal and ethical constraints. Sim…

Estimate relaxation times in nonextensive systems using gradient flow for Tsallis entropy maximization.

Optimizes basis functions for learning dynamical systems from data.

A new stochastic algorithm approximates optimal distributions without requiring propagation of chaos.

Stochastic gradient descent approximates Gaussian process posteriors efficiently.

Weak correlations explain linear dynamics in deep learning models.

The topological classification of gradient like Morse-Smale vector fields and diffeomorphisms on 3-manifolds was obtained.

New method preserves convergence rates in gradient-based optimization.

Derives exact gradients for linear optics with single photons.

The linear quadratic regulator (LQR) problem has reemerged as an important theoretical benchmark for reinforcement learning-based control of complex dynamical systems with continuous state and action spaces. In contrast with nearly all recent work in this area, we consider multiplicative noise models, which are increas…

Gradient-free framework for Bayesian experimental design in complex systems.

GFM models neural network training as a dynamical system to forecast final weights.

Researchers propose a non-monotone quantum natural gradient for quantum systems.

Article provides Bernstein gradient estimates for heat equations with potential terms.

In applications of Gaussian processes where quantification of uncertainty is of primary interest, it is necessary to accurately characterize the posterior distribution over covariance parameters. This paper proposes an adaptation of the Stochastic Gradient Langevin Dynamics algorithm to draw samples from the posterior …