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.
Single-timescale actor-critic finds globally optimal policy.
Proposes glocal hypergradient estimation for hyperparameter optimization.
Local adaptive methods in FL can accelerate convergence but introduce bias, which is corrected.
CRPO solves challenging SRL problems with convergence guarantee.
FedGLOMO accelerates FL convergence for non-convex functions.
We present ARU, an Adaptive Recurrent Unit for streaming adaptation of deep globally trained time-series forecasting models. The ARU combines the advantages of learning complex data transformations across multiple time series from deep global models, with per-series localization offered by closed-form linear models. Un…
We present an efficient alternating direction method of multipliers (ADMM) algorithm for segmenting a multivariate non-stationary time series with structural breaks into stationary regions. We draw from recent work where the series is assumed to follow a vector autoregressive model within segments and a convex estimati…
New quasi-Newton method guarantees global superlinear convergence.
FedFMC improves federated learning on non-iid data without sharing data or increasing communication costs.
Paper improves policy updates in reinforcement learning to speed up learning.
Edge devices learn a global model collaboratively over wireless channels.
Recently, the technique of local updates is a powerful tool in centralized settings to improve communication efficiency via periodical communication. For decentralized settings, it is still unclear how to efficiently combine local updates and decentralized communication. In this work, we propose an algorithm named as L…
Paper proves global convergence of NCELM model.
Study investigates FL performance over a noisy downlink, showing analog approach outperforms digital.
Many applications in signal processing benefit from the sparsity of signals in a certain transform domain or dictionary. Synthesis sparsifying dictionaries that are directly adapted to data have been popular in applications such as image denoising, inpainting, and medical image reconstruction. In this work, we focus in…
Federated learning is a method of training a global model from decentralized data distributed across client devices. Here, model parameters are computed locally by each client device and exchanged with a central server, which aggregates the local models for a global view, without requiring sharing of training data. The…
A new update rule for deep reinforcement learning reduces learning variance and variance in reference signals.
A framework for federated adversarial learning with convergence analysis.
Study reveals convergence properties of SGD with random learning rate.
GAIL with neural networks converges to global optima and has a known rate.
This paper shows how deep neural networks can learn rich, independent features that significantly deviate from initialization.
FedCONST adapts update magnitudes to enhance feature generalization in FL.
Paper proposes a quasi-Newton method for nonlinear equations with global convergence guarantees.
We describe -MLE, a fast and efficient local search algorithm for learning finite statistical mixtures of exponential families such as Gaussian mixture models. Mixture models are traditionally learned using the expectation-maximization (EM) soft clustering technique that monotonically increases the incomplete (expec…
Federated learning is a recently proposed paradigm that enables multiple clients to collaboratively train a joint model. It allows clients to train models locally, and leverages the parameter server to generate a global model by aggregating the locally submitted gradient updates at each round. Although the incentive mo…
Federated learning (FL) provides a communication-efficient approach to solve machine learning problems concerning distributed data, without sending raw data to a central server. However, existing works on FL only utilize first-order gradient descent (GD) and do not consider the preceding iterations to gradient update w…
Understanding the global optimality in deep learning (DL) has been attracting more and more attention recently. Conventional DL solvers, however, have not been developed intentionally to seek for such global optimality. In this paper we propose a novel approximation algorithm, BPGrad, towards optimizing deep models glo…
The paper analyzes dynamics of momentum in high dimensions with sparse updates.
Optimizers find approximate global minima in non-convex problems.
In this paper, we provide local and global convergence guarantees for recovering CP (Candecomp/Parafac) tensor decomposition. The main step of the proposed algorithm is a simple alternating rank- update which is the alternating version of the tensor power iteration adapted for asymmetric tensors. Local convergence g…
Deep Neural Network (DNN) is powerful but computationally expensive and memory intensive, thus impeding its practical usage on resource-constrained front-end devices. DNN pruning is an approach for deep model compression, which aims at eliminating some parameters with tolerable performance degradation. In this paper, w…
New method improves uncertainty quantification in latent variable models.
The paper proves convergence to global optima for a class of distributed algorithms for nonconvex optimization in network-based multi-agent settings. Agents are permitted to communicate over a time-varying undirected graph. Each agent is assumed to possess a local objective function (assumed to be smooth, but possibly …
A key aspect of Federated Learning (FL) is the requirement of a centralized aggregator to maintain and update the global model. However, in many cases orchestrating a centralized aggregator might be infeasible due to numerous operational constraints. In this paper, we introduce BAFFLE, an aggregator free, blockchain dr…
Study on incentivizing truthfulness in federated learning with heterogeneous data.
In this paper, we propose a distributed off-policy actor critic method to solve multi-agent reinforcement learning problems. Specifically, we assume that all agents keep local estimates of the global optimal policy parameter and update their local value function estimates independently. Then, we introduce an additional…
In this paper, we consider the problem of recovering a sparse signal based on penalized least squares formulations. We develop a novel algorithm of primal-dual active set type for a class of nonconvex sparsity-promoting penalties, including , bridge, smoothly clipped absolute deviation, capped and mini…
HPSGD speeds up DNN training by paralleling data sync with local training.
Paper develops NPG for risk-averse RL with ECRMs, proving global convergence.
Federated learning is a method of training models on private data distributed over multiple devices. To keep device data private, the global model is trained by only communicating parameters and updates which poses scalability challenges for large models. To this end, we propose a new federated learning algorithm that …
In this paper we revisit the weighted likelihood bootstrap, a method that generates samples from an approximate Bayesian posterior of a parametric model. We show that the same method can be derived, without approximation, under a Bayesian nonparametric model with the parameter of interest defined as minimising an expec…
Two-Timescale EM Methods improve EM for nonconvex models.
Inference problems in graphical models are often approximated by casting them as constrained optimization problems. Message passing algorithms, such as belief propagation, have previously been suggested as methods for solving these optimization problems. However, there are few convergence guarantees for such algorithms…
Ten sharp lower estimates of the first non-trivial eigenvalue of Laplacian on compact Riemannian manifolds are reviewed and compared. An improved variational formula, a general common estimate, and a new sharp one are added. The best lower estimates are now updated. The new estimates provide a global picture of what on…
Continuous-time distributed mirror descent with integral feedback converges to global optimum.
In many applications, the training data for a machine learning task is partitioned across multiple nodes, and aggregating this data may be infeasible due to communication, privacy, or storage constraints. Existing distributed optimization methods for learning global models in these settings typically aggregate local up…
Proposes a differentially private bandit algorithm reducing noise over time.
This letter presents an improved version of diffusion least mean ppower (LMP) algorithm for distributed estimation. Instead of sum of mean square errors, a weighted sum of mean square error is defined as the cost function for global and local cost functions of a network of sensors. The weight coefficients are updated b…