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.
A new restart criterion for k-means++ improves clustering quality and adapts to data difficulty.
Master algorithm fails to detect non-stationarity in practical settings.
New algorithms boost SAT solver performance by optimizing restart strategies.
Motivated by their broad applications in reinforcement learning, we study the linear two-time-scale stochastic approximation, an iterative method using two different step sizes for finding the solutions of a system of two equations. Our main focus is to characterize the finite-time complexity of this method under time-…
A new sampling method called Restart improves both speed and quality of generative processes.
New RL algorithm tackles nonstationary MDPs with linear approximations and varying rewards.
Paper adds a restart mechanism to a drawdown control policy for better trading performance.
Recent studies have shown that proximal gradient (PG) method and accelerated gradient method (APG) with restarting can enjoy a linear convergence under a weaker condition than strong convexity, namely a quadratic growth condition (QGC). However, the faster convergence of restarting APG method relies on the potentially …
Improved SEG method converges to Nash equilibrium in bilinear games.
We consider the generic approach of using an experience memory to help exploration by adapting a restart distribution. That is, given the capacity to reset the state with those corresponding to the agent's past observations, we help exploration by promoting faster state-space coverage via restarting the agent from a mo…
Paper tackles non-stationary kernelized bandits with near-optimal algorithm.
RePS improves diffusion models for solving inverse problems efficiently.
Study adapts combinatorial semi-bandit for piecewise stationary, causally related rewards.
State-of-the-art adversarial attacks on neural networks use expensive iterative methods and numerous random restarts from different initial points. Iterative FGSM-based methods without restarts trade off performance for computational efficiency because they do not adequately explore the image space and are highly sensi…
PROPO tackles non-stationary MDPs with efficient policy optimization.
This paper is concerned with improving the empirical convergence speed of block-coordinate descent algorithms for approximate nonnegative tensor factorization (NTF). We propose an extrapolation strategy in-between block updates, referred to as heuristic extrapolation with restarts (HER). HER significantly accelerates t…
Algorithm reduces decision-making errors in multi-agent bandit problems.
In this paper, we propose a distributed algorithm for stochastic smooth, non-convex optimization. We assume a worker-server architecture where nodes, each having (potentially infinite) number of samples, collaborate with the help of a central server to perform the optimization task. The global objective is to m…
Dual training method for EBMs with overparametrized neural networks.
Determinantal consensus clustering improves clustering robustness.
A new algorithm solves nonnegative least squares faster with nonnegative data.
WARPd method solves inverse problems with approximate sharpness conditions.
Unified approach for non-stationary linear bandits with dynamic regret.
BRPC online Bayesian calibration handles gradual and abrupt system changes.
In this paper we develop a Morse theory for the uniform energy. We use the one-sided directional derivative of the distance function to study the minimizing properties of variations through closed geodesics. This derivative is then used to define a one-sided directional derivative for the uniform energy which allows us…
Continuous optimization is an important problem in many areas of AI, including vision, robotics, probabilistic inference, and machine learning. Unfortunately, most real-world optimization problems are nonconvex, causing standard convex techniques to find only local optima, even with extensions like random restarts and …
We study the problem of minimizing a strongly convex, smooth function when we have noisy estimates of its gradient. We propose a novel multistage accelerated algorithm that is universally optimal in the sense that it achieves the optimal rate both in the deterministic and stochastic case and operates without knowledge …
There is a general trend towards solving problems suited to deep learning with more complex deep learning architectures trained on larger training sets. This requires longer compute times and greater data parallelization or model parallelization. Both data and model parallelism have been historically faster in paramete…
PER-ETD improves ETD by reducing variance to polynomial complexity.
One-pass optimisation for high-dimensional hyperparameters.
This paper refines the weighted strategy for non-stationary parametric bandits, improving regret bounds.
We derive an optimal policy for adaptively restarting a randomized algorithm, based on observed features of the run-so-far, so as to minimize the expected time required for the algorithm to successfully terminate. Given a suitable Bayesian prior, this result can be used to select the optimal black-box optimization algo…
Novel methods for accelerating optimization in complex bilevel and minimax problems.
New algorithm tackles non-stationary RL with near-optimal regret bounds.
New method finds near-optimal solutions for non-convex optimization problems.
This paper proposes a novel profile likelihood method for estimating the covariance parameters in exploratory factor analysis of high-dimensional Gaussian datasets with fewer observations than number of variables. An implicitly restarted Lanczos algorithm and a limited-memory quasi-Newton method are implemented to deve…
SRSGD improves DNN training speed and accuracy.
Heuristic optimisers which search for an optimal configuration of variables relative to an objective function often get stuck in local optima where the algorithm is unable to find further improvement. The standard approach to circumvent this problem involves periodically restarting the algorithm from random initial con…
New method tracks significant arm switches to improve bandit algorithms.
We present a framework for Nesterov's accelerated gradient flows in probability space to design efficient mean-field Markov chain Monte Carlo (MCMC) algorithms for Bayesian inverse problems. Here four examples of information metrics are considered, including Fisher-Rao metric, Wasserstein-2 metric, Kalman-Wasserstein m…
We derive a second-order ordinary differential equation (ODE) which is the limit of Nesterov's accelerated gradient method. This ODE exhibits approximate equivalence to Nesterov's scheme and thus can serve as a tool for analysis. We show that the continuous time ODE allows for a better understanding of Nesterov's schem…
This paper refines the weighted strategy for non-stationary parametric bandits and MDPs, improving regret bounds.
Online distributional prediction with latent cluster geometry
LLMs optimize quantum circuits by iteratively improving proposals with feedback and memory traces.
A parameter-free PGD algorithm for convex optimization.
In this paper, we study the proximal gradient algorithm with extrapolation for minimizing the sum of a Lipschitz differentiable function and a proper closed convex function. Under the error bound condition used in [19] for analyzing the convergence of the proximal gradient algorithm, we show that there exists a thresho…
Recent advances in Neural Architecture Search (NAS) have produced state-of-the-art architectures on several tasks. NAS shifts the efforts of human experts from developing novel architectures directly to designing architecture search spaces and methods to explore them efficiently. The search space definition captures pr…
Generative adversarial networks (GAN) are a powerful subclass of generative models. Despite a very rich research activity leading to numerous interesting GAN algorithms, it is still very hard to assess which algorithm(s) perform better than others. We conduct a neutral, multi-faceted large-scale empirical study on stat…