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.
Quantum computing promises faster finance algorithms.
Quantum computing offers a quadratic speedup for estimating non-linear functionals.
Quantum algorithm speeds up nested expectation estimation by nearly quadratically.
Quantum algorithm speeds up learning from big data exponentially.
Quantum algorithms speed up derivative pricing beyond Black-Scholes models.
A central task in the field of quantum computing is to find applications where quantum computer could provide exponential speedup over any classical computer. Machine learning represents an important field with broad applications where quantum computer may offer significant speedup. Several quantum algorithms for discr…
Federated Q-Learning achieves linear regret speedup with low communication cost.
Quantum algorithm speeds up MIP solving by a near-quadratic factor.
GPU optimization speeds up large-scale classification tasks.
ProxSkip achieves linear speedup in distributed non-convex optimization.
With the increase in the amount of data and the expansion of model scale, distributed parallel training becomes an important and successful technique to address the optimization challenges. Nevertheless, although distributed stochastic gradient descent (SGD) algorithms can achieve a linear iteration speedup, they are l…
Unified analysis of Federated Averaging and Nesterov FedAvg for linear speedup.
We develop parallel and distributed Frank-Wolfe algorithms; the former on shared memory machines with mini-batching, and the latter in a delayed update framework. Whenever possible, we perform computations asynchronously, which helps attain speedups on multicore machines as well as in distributed environments. Moreover…
ECD algorithm speeds up non-convex optimization, offering quantum and stochastic enhancements.
New algorithm achieves linear speedup in non-i.i.d. federated bilevel learning.
We present CYCLADES, a general framework for parallelizing stochastic optimization algorithms in a shared memory setting. CYCLADES is asynchronous during shared model updates, and requires no memory locking mechanisms, similar to HOGWILD!-type algorithms. Unlike HOGWILD!, CYCLADES introduces no conflicts during the par…
Efficiently approximates Sparse PCA with significant speedups and minor error.
Speeds up deep neural networks training by 10x using GPU concurrency.
We describe ASAGA, an asynchronous parallel version of the incremental gradient algorithm SAGA that enjoys fast linear convergence rates. Through a novel perspective, we revisit and clarify a subtle but important technical issue present in a large fraction of the recent convergence rate proofs for asynchronous parallel…
Recurrent neural networks (RNN) have been successfully applied to various sequential decision-making tasks, natural language processing applications, and time-series predictions. Such networks are usually trained through back-propagation through time (BPTT) which is prohibitively expensive, especially when the length o…
The realized stochastic volatility (RSV) model that utilizes the realized volatility as additional information has been proposed to infer volatility of financial time series. We consider the Bayesian inference of the RSV model by the Hybrid Monte Carlo (HMC) algorithm. The HMC algorithm can be parallelized and thus per…
In machine learning, asynchronous parallel stochastic gradient descent (APSGD) is broadly used to speed up the training process through multi-workers. Meanwhile, the time delay of stale gradients in asynchronous algorithms is generally proportional to the total number of workers, which brings additional deviation from …
Improved K-Means++ and K-Means with faster run-time.
DASA speeds up SA with delayed agents, achieving N-fold speedup.
Recent studies have illustrated that stochastic gradient Markov Chain Monte Carlo techniques have a strong potential in non-convex optimization, where local and global convergence guarantees can be shown under certain conditions. By building up on this recent theory, in this study, we develop an asynchronous-parallel s…
Quantum algorithm estimates mean with sub-Gaussian error.
Two algorithms improve K-means clustering speed without sacrificing quality.
Federated learning is a new distributed machine learning framework, where a bunch of heterogeneous clients collaboratively train a model without sharing training data. In this work, we consider a practical and ubiquitous issue when deploying federated learning in mobile environments: intermittent client availability, w…
Best arm identification (or, pure exploration) in multi-armed bandits is a fundamental problem in machine learning. In this paper we study the distributed version of this problem where we have multiple agents, and they want to learn the best arm collaboratively. We want to quantify the power of collaboration under limi…
We develop the first quantum algorithm for the constrained portfolio optimization problem. The algorithm has running time , where is the number of positivity and budget constraints, is the number of assets in the portfolio, the des…
Optimized parallel algorithms for identifying strong ties in data.
New algorithms tackle complex multi-block optimization problems in machine learning.
Given a similarity graph between items, correlation clustering (CC) groups similar items together and dissimilar ones apart. One of the most popular CC algorithms is KwikCluster: an algorithm that serially clusters neighborhoods of vertices, and obtains a 3-approximation ratio. Unfortunately, KwikCluster in practice re…
Federated Q-learning achieves linear speedup with heterogeneity, improving sample complexity.
This paper advances FL algorithms for composite optimization and statistical recovery.
Clustering algorithms are a cornerstone of machine learning applications. Recently, a quantum algorithm for clustering based on the k-means algorithm has been proposed by Kerenidis, Landman, Luongo and Prakash. Based on their work, we propose a quantum expectation-maximization (EM) algorithm for Gaussian mixture models…
Paper presents an efficient algorithm for learning minimax risk classifiers with large-scale data.
Improved neural framework for scaling entropic MOT with significant computational gains.
A fast method for Lasso and Logistic Lasso problems.
New insights explain speedup saturation in distributed learning with large batches and delays.
We are interested in parallelizing the Least Angle Regression (LARS) algorithm for fitting linear regression models to high-dimensional data. We consider two parallel and communication avoiding versions of the basic LARS algorithm. The two algorithms have different asymptotic costs and practical performance. One offers…
In this work we show that randomized (block) coordinate descent methods can be accelerated by parallelization when applied to the problem of minimizing the sum of a partially separable smooth convex function and a simple separable convex function. The theoretical speedup, as compared to the serial method, and referring…
Efficient medoid-based Silhouette method speeds up clustering evaluation.
Clustering non-Euclidean data is difficult, and one of the most used algorithms besides hierarchical clustering is the popular algorithm Partitioning Around Medoids (PAM), also simply referred to as k-medoids. In Euclidean geometry the mean-as used in k-means-is a good estimator for the cluster center, but this does no…
We propose a stochastic variance reduced optimization algorithm for solving sparse learning problems with cardinality constraints. Sufficient conditions are provided, under which the proposed algorithm enjoys strong linear convergence guarantees and optimal estimation accuracy in high dimensions. We further extend the …
Predicting structured outputs can be computationally onerous due to the combinatorially large output spaces. In this paper, we focus on reducing the prediction time of a trained black-box structured classifier without losing accuracy. To do so, we train a speedup classifier that learns to mimic a black-box classifier u…
Paper proposes FedQ-Advantage for federated Q-learning with near-optimal regret and low communication cost.
We present a parallel algorithm that computes the ask and bid prices of an American option when proportional transaction costs apply to the trading of the underlying asset. The algorithm computes the prices on recombining binomial trees, and is designed for modern multi-core processors. Although parallel option pricing…