A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Paper analyzes \FedAvg's convergence and introduces a new algorithm to reduce bias.
Paper analyzes LSA algorithm bias and error bounds with RR extrapolation.
Paper proposes a new algorithm to reduce derivative pricing computation time.
The paper analyzes SGD with Richardson-Romberg extrapolation for convex optimization problems.
Paper examines constant stepsize in LSA for Markovian data inference.
Study on bias of constant-step stochastic approximation with Markovian noise.
Study Q-learning with constant stepsize, proving convergence and bias, and applying extrapolation.
Study on bias and extrapolation in LSA with Markovian data, showing bias reduction with Richardson-Romberg extrapolation.
We consider the minimization of an objective function given access to unbiased estimates of its gradient through stochastic gradient descent (SGD) with constant step-size. While the detailed analysis was only performed for quadratic functions, we provide an explicit asymptotic expansion of the moments of the averaged S…
Study on nonsmooth contractive SA with constant stepsize and Q-learning.
New insights into stochastic methods for solving variational inequalities.