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.
Accelerates machine learning algorithms for sparse data.
The paper explores dual learning, a technique that improves machine translation and image transformation.
Dual PC algorithm improves structure learning of Bayesian networks.
PDCA algorithm learns policies for RL with constraints using a primal-dual approach.
Paper develops Byzantine-resilient algorithms for decentralized learning.
Optimizes subset selection in sparse learning problems.
Efficient algorithm solves best subset selection problem.
Paper proposes a novel metric learning algorithm using Riemannian optimization.
New algorithm for federated learning with non-smooth regularizers.
New algorithm achieves sublinear regret in CMDPs without error cancellations.
Recently, considerable research efforts have been devoted to the design of methods to learn from data overcomplete dictionaries for sparse coding. However, learned dictionaries require the solution of an optimization problem for coding new data. In order to overcome this drawback, we propose an algorithm aimed at learn…
In this paper, we propose a dual memory structure for reinforcement learning algorithms with replay memory. The dual memory consists of a main memory that stores various data and a cache memory that manages the data and trains the reinforcement learning agent efficiently. Experimental results show that the dual memory …
Given a convex optimization problem and its dual, there are many possible first-order algorithms. In this paper, we show the equivalence between mirror descent algorithms and algorithms generalizing the conditional gradient method. This is done through convex duality, and implies notably that for certain problems, such…
Previous studies on stochastic primal-dual algorithms for solving min-max problems with faster convergence heavily rely on the bilinear structure of the problem, which restricts their applicability to a narrowed range of problems. The main contribution of this paper is the design and analysis of new stochastic primal-d…
We consider the problem of a firm seeking to use personalized pricing to sell an exogenously given stock of a product over a finite selling horizon to different consumer types. We assume that the type of an arriving consumer can be observed but the demand function associated with each type is initially unknown. The fir…
Algorithm optimizes constrained reinforcement learning with dual variables.
Improved RL algorithm with linear MDPs for offline learning with partial data coverage.
Sketching techniques have become popular for scaling up machine learning algorithms by reducing the sample size or dimensionality of massive data sets, while still maintaining the statistical power of big data. In this paper, we study sketching from an optimization point of view: we first show that the iterative Hessia…
We consider empirical risk minimization of linear predictors with convex loss functions. Such problems can be reformulated as convex-concave saddle point problems, and thus are well suitable for primal-dual first-order algorithms. However, primal-dual algorithms often require explicit strongly convex regularization in …
Dual learning algorithm addresses delayed conversions in CVR prediction.
Paper analyzes and compares ELF algorithms for federated learning.
A distributed algorithm for online multi-task learning reduces communication and runtime costs.
Efficient federated algorithm for calculating transportation barycenter.
The stochastic dual coordinate-ascent (S-DCA) technique is a useful alternative to the traditional stochastic gradient-descent algorithm for solving large-scale optimization problems due to its scalability to large data sets and strong theoretical guarantees. However, the available S-DCA formulation is limited to finit…
Study efficient convergence of RL algorithm with function approximation.
New algorithm learns optimal resource allocation in wireless systems without models.
Dual training method for EBMs with overparametrized neural networks.
Paper tackles offline RL with weak assumptions on both function classes and data coverage.
A new method for faster optimization on statistical manifolds.
Dual behavior policy improves reinforcement learning across various environments.
We introduce Primal-Dual Wasserstein GAN, a new learning algorithm for building latent variable models of the data distribution based on the primal and the dual formulations of the optimal transport (OT) problem. We utilize the primal formulation to learn a flexible inference mechanism and to create an optimal approxim…
PDA method optimizes neural networks with global convergence rate analysis.
Drago optimizes DRO problems with faster convergence.
Multi-task learning aims to learn multiple tasks jointly by exploiting their relatedness to improve the generalization performance for each task. Traditionally, to perform multi-task learning, one needs to centralize data from all the tasks to a single machine. However, in many real-world applications, data of differen…
Despite the success of single-agent reinforcement learning, multi-agent reinforcement learning (MARL) remains challenging due to complex interactions between agents. Motivated by decentralized applications such as sensor networks, swarm robotics, and power grids, we study policy evaluation in MARL, where agents with jo…
Iterative Hard Thresholding (IHT) is a class of projected gradient descent methods for optimizing sparsity-constrained minimization models, with the best known efficiency and scalability in practice. As far as we know, the existing IHT-style methods are designed for sparse minimization in primal form. It remains open t…
The paper extends NUP representations to factor graphs for better estimation.
New algorithm reduces regret in CMDPs without cancellation of errors.
We provide theoretical complexity analysis for new algorithms to compute the optimal transport (OT) distance between two discrete probability distributions, and demonstrate their favorable practical performance over state-of-art primal-dual algorithms and their capability in solving other problems in large-scale, such …
New dual approach for hedging Bermudan options efficiently.
One of the popular approaches for low-rank tensor completion is to use the latent trace norm regularization. However, most existing works in this direction learn a sparse combination of tensors. In this work, we fill this gap by proposing a variant of the latent trace norm that helps in learning a non-sparse combinatio…
Dual-structured method improves cross-domain imitation learning.
FeDualEx tackles saddle point optimization in federated learning with composite objectives.
A simpler edge-based discretization method without dual volumes.
We develop a primal dual active set with continuation algorithm for solving the \ell^0-regularized least-squares problem that frequently arises in compressed sensing. The algorithm couples the the primal dual active set method with a continuation strategy on the regularization parameter. At each inner iteration, it fir…
Unified algorithm solves convex optimization problems with optimal rates.
In decentralized networks (of sensors, connected objects, etc.), there is an important need for efficient algorithms to optimize a global cost function, for instance to learn a global model from the local data collected by each computing unit. In this paper, we address the problem of decentralized minimization of pairw…
Inferring a person's goal from their behavior is an important problem in applications of AI (e.g. automated assistants, recommender systems). The workhorse model for this task is the rational actor model - this amounts to assuming that people have stable reward functions, discount the future exponentially, and construc…