arXiv research

New method for natural policy gradients converges linearly.

New method shows hidden state can significantly improve differential privacy in SGD.

This paper introduces SS-MAMP to address convergence issues in AMP algorithms.

A new RL paradigm reduces state-action-value function approximation inefficiency.

This paper analyzes discrete diffusion models, deriving convergence bounds for their generated samples.

Portfolio turnpikes state that, as the investment horizon increases, optimal portfolios for generic utilities converge to those of isoelastic utilities. This paper proves three kinds of turnpikes. In a general semimartingale setting, the abstract turnpike states that optimal final payoffs and portfolios converge under …

The paper proves almost sure convergence of MCES algorithm for a specific class of MDPs.

Study provides convergence guarantees for discrete diffusion models on finite and infinite state spaces.

The abstract discusses convergence properties of Lipschitz functions and sets defined by equations.

Characterizes problems solvable via linear convergence algorithms.

Algorithm converges to Nash equilibria in competitive games.

Novel framework proves fast RL convergence in continuous spaces.

New optimizer G-AdaGrad improves upon AdaGrad for non-convex machine learning problems.

Study on Neural Tangent Kernel of Matrix Product States and their convergence.

This study analyses, through cross-section estimation methods, the influence of spatial effects and human capital in the conditional productivity convergence (product per worker) in the economic sectors of NUTs III of mainland Portugal between 1995 and 2002. To analyse the data, Moran's I statistics is considered, and …

Operator calculus for population-based optimization provides a unified framework for analyzing convergence of various methods.

The paper proves convergence of normalized Ricci flow on compact manifolds.

RWR converges to global optimum in certain settings.

Study on nonsmooth contractive SA with constant stepsize and Q-learning.

We study discrete time dynamical systems governed by the state equation $h_{t+1}=φ(Ah_t+Bu_t)$. Here $A,B$ are weight matrices, $φ$ is an activation function, and $u_t$ is the input data. This relation is the backbone of recurrent neural networks (e.g. LSTMs) which have broad applications in sequential learning tasks. …

Improved uniform convergence bound with fat-shattering dimension reduces sample complexity gap.

This work develops a fully decentralized multi-agent algorithm for policy evaluation. The proposed scheme can be applied to two distinct scenarios. In the first scenario, a collection of agents have distinct datasets gathered following different behavior policies (none of which is required to explore the full state spa…

New proof shows local wealth condensation in economic models with biases.

Study controlled contagion with state-dependent killing, proving a comparison principle.

The paper simplifies multi-agent RL dynamics in finite-state Markov games using homogenization.

Distributed strategic learning has been getting attention in recent years. As systems become distributed finding Nash equilibria in a distributed fashion is becoming more important for various applications. In this paper, we develop a distributed strategic learning framework for seeking Nash equilibria under stochastic…

New quantum state reconstruction method accelerates convergence.

Proposes a new method for GNNs that avoids iterative node state convergence.

Sketch Tomography improves quantum state estimation accuracy.

This study analyses, through cross-section estimation methods, the influence of spatial effects in the conditional product convergence in the parishes' economies of mainland Portugal between 1991 and 2001 (the last year with data available for this spatial disaggregation level). To analyse the data, Moran's I statistic…

New method speeds up Gibbs sampling for large graphs.

Counterfactual Regret Minimization (CFR) has found success in settings like poker which have both terminal states and perfect recall. We seek to understand how to relax these requirements. As a first step, we introduce a simple algorithm, local no-regret learning (LONR), which uses a Q-learning-like update rule to allo…

A new estimator for state values in reinforcement learning reduces complexity and improves convergence.

Investigates fund separations and stability for long-term optimal investments.

In this paper we analyze, evaluate, and improve the performance of training generalized linear models on modern CPUs. We start with a state-of-the-art asynchronous parallel training algorithm, identify system-level performance bottlenecks, and apply optimizations that improve data parallelism, cache line locality, and …

The paper analyzes Q-learning convergence rates with asynchronous updates.

SS-SARSA tackles recovering bandits by treating rounds as states.

Combining insights from machine learning and quantum Monte Carlo, the stochastic reconfiguration method with neural network Ansatz states is a promising new direction for high-precision ground state estimation of quantum many-body problems. Even though this method works well in practice, little is known about the learn…

The time to converge to the steady state of a finite Markov chain can be greatly reduced by a lifting operation, which creates a new Markov chain on an expanded state space. For a class of quadratic objectives, we show an analogous behavior where a distributed ADMM algorithm can be seen as a lifting of Gradient Descent…

Study improves covariance estimation for SGD under Markovian data, matching best rates.

The objective is to study an on-line Hidden Markov model (HMM) estimation-based Q-learning algorithm for partially observable Markov decision process (POMDP) on finite state and action sets. When the full state observation is available, Q-learning finds the optimal action-value function given the current action (Q func…

In this paper, we prove some convergence results of a special case of optimistic policy iteration algorithm for stochastic shortest path problem. We consider both Monte Carlo and $TD(λ)$ methods for the policy evaluation step under the condition that the termination state will eventually be reached almost surely.

Efficient RNN algorithm guarantees convergence in online learning.

We revisit the development of grid based recursive approximate filtering of general Markov processes in discrete time, partially observed in conditionally Gaussian noise. The grid based filters considered rely on two types of state quantization: The \textit{Markovian} type and the \textit{marginal} type. We propose a s…

Policy gradient methods achieve linear convergence in simple MDPs.

Kernel learning FBSDE filter improves nonlinear filtering efficiency.

The principle of convergence stability for geometric flows is the combination of the continuous dependence of the flow on initial conditions, with the stability of fixed points. It implies that if the flow from an initial state $g_0$ exists for all time and converges to a stable fixed point, then the flows of solutions…

Study on natural actor-critic for POMDPs with finite memory.