arXiv research

SINDy-PI robustly identifies implicit dynamics from noisy data.

Two heuristics solve dynamic multiple travelling salesmen problems.

We demonstrate the possibility of classifying causal systems into kinds that share a common structure without first constructing an explicit dynamical model or using prior knowledge of the system dynamics. The algorithmic ability to determine whether arbitrary systems are governed by causal relations of the same form o…

Hamiltonian dynamics-based algorithms achieve deterministic and accelerated convergence for convex optimization.

Approximate dynamic programming algorithms, such as approximate value iteration, have been successfully applied to many complex reinforcement learning tasks, and a better approximate dynamic programming algorithm is expected to further extend the applicability of reinforcement learning to various tasks. In this paper w…

Review of algorithms for linear system approximations.

Paper tackles reinforcement learning with complex observations and simple latent dynamics.

Adaptive algorithm improves convergence rate of Langevin dynamics.

Temporal-difference (TD) networks are a class of predictive state representations that use well-established TD methods to learn models of partially observable dynamical systems. Previous research with TD networks has dealt only with dynamical systems with finite sets of observations and actions. We present an algorithm…

Algorithm learns dynamics from past observations.

Improved algorithm for adaptive dueling bandits with near-optimal regret bound.

Dynamic Sparse Training finds efficient sparse networks from scratch.

New loss function helps learn unstable dynamical systems.

New algorithm reduces performance loss in IRL with mismatched transition dynamics.

New algorithm reduces dynamic regret without prior function change knowledge.

This paper learns state, dynamics, and filtering algorithms together for data assimilation.

Despite the importance of sparsity signal models and the increasing prevalence of high-dimensional streaming data, there are relatively few algorithms for dynamic filtering of time-varying sparse signals. Of the existing algorithms, fewer still provide strong performance guarantees. This paper examines two algorithms f…

Reinforcement learning would enjoy better success on real-world problems if domain knowledge could be imparted to the algorithm by the modelers. Most problems have both hidden state and unknown dynamics. Partially observable Markov decision processes (POMDPs) allow for the modeling of both. Unfortunately, they do not p…

Proposes a dynamic matching algorithm for two-sided online markets.

New algorithm learns linear dynamical systems from measurements.

The paper develops a new algorithm for RBMs using dynamical mean-field theory.

Paper discovers structural dynamics equations from only acceleration data.

Randomized SINDy learns dynamic data structures using probabilistic methods.

New algorithm models satiation in recommender systems.

AdaBoost cycles in probability simplex dynamics.

In this paper we apply active learning algorithms for dynamic pricing in a prominent e-commerce website. Dynamic pricing involves changing the price of items on a regular basis, and uses the feedback from the pricing decisions to update prices of the items. Most popular approaches to dynamic pricing use a passive learn…

New algorithms reduce dynamic regret in non-stationary RL environments.

Linear dynamical systems are a fundamental and powerful parametric model class. However, identifying the parameters of a linear dynamical system is a venerable task, permitting provably efficient solutions only in special cases. This work shows that the eigenspectrum of unknown linear dynamics can be identified without…

In this paper, we propose a dynamical systems perspective of the Expectation-Maximization (EM) algorithm. More precisely, we can analyze the EM algorithm as a nonlinear state-space dynamical system. The EM algorithm is widely adopted for data clustering and density estimation in statistics, control systems, and machine…

Study explores algorithmic collusion in repeated games using various learning dynamics.

Universal online optimization for dynamic environments using uniclass prediction.

We demonstrate the application of an algorithmic trading strategy based upon the recently developed dynamic mode decomposition (DMD) on portfolios of financial data. The method is capable of characterizing complex dynamical systems, in this case financial market dynamics, in an equation-free manner by decomposing the s…

Regret minimization is treated as the golden rule in the traditional study of online learning. However, regret minimization algorithms tend to converge to the static optimum, thus being suboptimal for changing environments. To address this limitation, new performance measures, including dynamic regret and adaptive regr…

Study dynamic matching in heterogeneous networks using ODE model.

New algorithm adapts to unknown demand smoothness for dynamic pricing.

Developed a new algorithm to improve dynamic treatment regimens.

This paper develops nudging algorithms using learned surrogates for state estimation in dynamical systems.

A new algorithm flattens multi-modal distributions for better deep learning.

A fast spectral algorithm detects community structure in evolving graphs.

Most real world phenomena such as sunlight distribution under a forest canopy, minerals concentration, stock valuation, exhibit nonstationary dynamics i.e. phenomenon variation changes depending on the locality. Nonstationary dynamics pose both theoretical and practical challenges to statistical machine learning algori…

The study analyzes momentum-based optimization algorithms from dynamical systems perspective.

Dynamic topic models (DTMs) are very effective in discovering topics and capturing their evolution trends in time series data. To do posterior inference of DTMs, existing methods are all batch algorithms that scan the full dataset before each update of the model and make inexact variational approximations with mean-fie…

This paper compares eight DRL algorithms for dynamic hedging.

Recursive least-squares algorithms often use forgetting factors as a heuristic to adapt to non-stationary data streams. The first contribution of this paper rigorously characterizes the effect of forgetting factors for a class of online Newton algorithms. For exp-concave and strongly convex objectives, the algorithms a…

Proposes a differentially private bandit algorithm reducing noise over time.

Algorithm learns optimal dynamic mechanisms from data.

Graph Neural Networks align with dynamic programming, improving algorithmic reasoning.

Improved RL algorithm stabilizes unknown linear systems with polynomial regret.