Research
On-device research index

arXiv research

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.

168,695 papers · 148 categories

Trend · papers per month

137275412549 · Jun 202019922001200920172026
48 results for Stochastic Gradient Tracking

Momentum SGD fails to track nonstationary optima due to drift amplification.

problem Tracking nonstationary optima in stochastic optimization.
method Theoretical analysis of SGD and momentum variants under strong convexity and smoothness.
result Momentum incurs a drift-amplification penalty that diverges as the momentum parameter approaches 1, leading to systematic lag.

In this paper, we study the problem of distributed multi-agent optimization over a network, where each agent possesses a local cost function that is smooth and strongly convex. The global objective is to find a common solution that minimizes the average of all cost functions. Assuming agents only have access to unbiase…

2018-05-25abs ↗pdf ↗

VRSGT algorithm reduces orthogonality constraints in decentralized optimization.

problem Decentralized optimization with orthogonality constraints.
method VRSGT algorithm with variance reduction and orthogonal techniques.
result VRSGT achieves convergence rate of O(1 / k) for orthogonality constraints.

A new method for distributed optimization with noisy function evaluations.

problem Distributed optimization with noisy function evaluations.
method Zero-order one-point estimate with distributed stochastic gradient-tracking technique.
result The method converges almost surely to the optimum with a rate of O(1k)O(\frac{1}{\sqrt{k}}).

Gradient filters track moving parameters under noisy data and misspecification.

problem Tracking multidimensional time-varying parameters under noisy observations and model misspecification.
method Gradient-based filters update parameters using the gradient of a postulated objective function, evaluated at either the predicted or updated parameters.
result Novel sufficient conditions for exponential stability of the filtered parameter path, and finite-sample and asymptotic mean squared error bounds.

Unified framework for decentralized optimization combining gradient tracking and variance reduction.

problem Solving finite-sum minimization problems in distributed systems with privacy and resource constraints.
method Unified algorithmic framework combining variance-reduction and gradient tracking.
result Unified methods achieve robust performance and fast convergence for smooth and strongly-convex objectives, and are applicable to non-convex problems.

Push-SAGA is a decentralized algorithm for directed graphs that converges linearly.

problem Finite-sum minimization over directed graphs with stochastic gradients.
method Combines variance reduction, gradient tracking, and consensus algorithms.
result Achieves linear convergence for smooth and strongly convex problems.

A new algorithm for decentralized optimization over directed graphs.

problem Decentralized stochastic optimization over directed networks.
method Gradient tracking and S-ADDOPT algorithm with constant and decaying step-sizes.
result S-ADDOPT converges linearly with constant step-size and sublinearly with decaying step-size.

Optimizes decisions in time-varying distributions using online stochastic methods and Wasserstein distance.

problem Optimizing decisions in time-varying distributions using Wasserstein distance.
method Online proximal-gradient method, exact penalty method, constraint-tightening approach.
result Dynamic regret bounds for tracking and estimation error.

Improved convergence analysis for decentralized non-convex optimization.

problem Minimizing a sum of smooth non-convex functions over a network.
method Gradient tracking in decentralized stochastic gradient descent (GT-DSGD).
result GT-DSGD achieves network-independent performances matching centralized SGD under certain conditions.

A method for estimating the median of gradients in stochastic optimization.

problem Robust gradient estimation in stochastic optimization for various applications.
method Stochastic Proximal Point Method for median gradient estimation.
result The proposed method can converge even under heavy-tailed, state-dependent noise.

High-probability bound for distributed stochastic approximation tracking error.

problem Analyzing the convergence of distributed stochastic approximation schemes.
method Analysis using ODE approach to stochastic approximation.
result High probability bound for tracking error between iterates and limiting differential equation.

Analysis of SGD for Gaussian mixture classification using dynamical mean-field theory.

problem Learning dynamics of SGD for a neural network classifying Gaussian mixture.
method Applying dynamical mean-field theory to track SGD dynamics in high dimensions.
result Reveals how SGD navigates the non-convex loss landscape.

AB-SAGA optimizes distributed optimization over directed graphs using variance reduction and stochastic weights.

problem Optimizing distributed stochastic optimization over directed graphs with stochastic weights.
method AB-SAGA combines variance reduction and network-level gradient tracking, using both row and column stochastic weights.
result AB-SAGA converges linearly to the global optimal with a constant step-size and achieves a linear speed-up over centralized methods.

Online learners track optimal solutions with constant step-size.

problem Tracking optimal solutions in online learning settings.
method Established a link between steady-state performance and tracking performance using analogies with adaptive filters.
result Inferred tracking performance from steady-state expressions directly.

GT-SARAH optimizes decentralized non-convex problems with recursive variance reduction.

problem Decentralized non-convex optimization of NN functions over a network.
method Stochastic first-order gradient method with SARAH variance reduction and gradient tracking.
result Achieves εε-accurate first-order stationary point with improved gradient complexity.

Paper proposes Langevin dynamics for adaptive IRL of stochastic gradient algorithms.

problem Estimating reward functions from noisy gradient estimates of stochastic gradient agents.
method Generalized Langevin dynamics algorithm for IRL.
result Proposed algorithms asymptotically generate samples proportional to exp(R(θ)).

This study models target trajectories using stochastic processes for efficient tracking.

problem Efficiently modeling and predicting target trajectories in continuous time.
method Decomposes trajectory modeling into deterministic and stochastic components using Gaussian or Student's-tt processes.
result Demonstrates superior performance in tracking maneuvering targets compared to existing methods.

The paper solves a control problem using reflections to track a benchmark process.

problem Optimal consumption with a benchmark process that grows over time.
method Introduced two auxiliary state processes with reflections to transform the problem into a more tractable form.
result Established the existence of a unique classical solution to the dual PDE.

Paper proposes adaptive control for unknown systems using reinforcement learning.

problem Adaptive control for unknown, linearizable systems.
method On-policy reinforcement learning for discrete-time, stochastic systems.
result Stability and tracking errors concentrate near zero with high probability.

The paper extends Merton's problem by adding benchmark tracking, finding optimal strategies.

problem Maximizing consumption utility with a trade-off against benchmark performance.
method Developed a convex duality theorem and derived optimal strategies for specific cases.
result Found optimal portfolio and consumption strategies for CRRA utility and geometric Brownian motion benchmarks.

The paper analyzes Adam and SGD in nonstationary optimization, revealing tradeoffs between noise and drift.

problem Analyzing Adam and SGD in nonstationary optimization problems.
method Theoretical analysis of Adam and SGD under non-stationary stochastic objectives, separating two regimes.
result Characterizes the tradeoff between noise and drift in Adam and SGD, revealing when adaptive step-sizing is beneficial or harmful.

Paper introduces MoTEF for faster decentralized optimization with compressed communication.

problem Efficiency bottleneck in decentralized machine learning applications.
method Integrates communication compression with Momentum Tracking and Error Feedback.
result Significantly outperforms existing methods under arbitrary data heterogeneity.

Two algorithms improve federated learning efficiency and resilience.

problem Scalability issues in federated learning due to communication, privacy, and Byzantine attacks.
method Proposes two algorithms, Ada-StoSign and ββ-StoSign, that compress gradients into bit vectors to reduce communication.
result Ada-StoSign converges with a rate of O(logT/T+1/M)O(\log T/\sqrt{T} + 1/\sqrt{M}) and outperforms existing methods.

New algorithms reduce online learning regret by tracking gradient variation.

problem Online learning with unconstrained losses and gradient variation.
method Parameter-free algorithms with adaptive updates for LL-smooth convex losses.
result Regret bounds of order O~(uVT(u)+Lu2+G4)\widetilde{O}(\|u\|\sqrt{V_T(u)} + L\|u\|^2+G^4) achieved without prior knowledge of comparator norm or Lipschitz constant.

Adaptive gradient methods such as Adam have been shown to be very effective for training deep neural networks (DNNs) by tracking the second moment of gradients to compute the individual learning rates. Differently from existing methods, we make use of the most recent first moment of gradients to compute the individual …

2019-02-24abs ↗pdf ↗

DESTRESS optimizes decentralized nonconvex optimization with optimal IFO complexity and efficient communication.

problem Decentralized nonconvex finite-sum optimization in multi-agent systems.
method DESTRESS uses stochastic recursive gradient updates, gradient tracking, and careful hyper-parameter choices to achieve optimal IFO complexity with efficient communication.
result DESTRESS matches the optimal IFO complexity of centralized algorithms while maintaining communication efficiency.

A novel decentralized algorithm improves minimax optimization in federated learning.

problem Minimax optimization in federated learning with data heterogeneity.
method Decentralized Gradient Tracking (K-GT-Minimax) for nonconvex-strongly-concave optimization.
result Demonstrates superior convergence rate for NC-SC minimax optimization.