Riemannian stochastic gradient descent approximates a diffusion process called Riemannian stochastic modified flow.
problem Improving convergence rate of Riemannian stochastic gradient descent.
method Using stochastic differential geometry, the paper shows RSGD can be approximated by the Riemannian stochastic modified flow (RSMF).
result RSGD can be approximated by the solution to the RSMF driven by an infinite-dimensional Wiener process, increasing the order of approximation.
Stochastic gradient descent is a simple approach to find the local minima of a cost function whose evaluations are corrupted by noise. In this paper, we develop a procedure extending stochastic gradient descent algorithms to the case where the function is defined on a Riemannian manifold. We prove that, as in the Eucli…
Riemannian stochastic gradient descent converges faster with increasing batch size.
problem Improving convergence rate of Riemannian stochastic gradient descent.
method Theoretical analysis and numerical investigation of increasing batch size effects.
result Riemannian stochastic gradient descent converges faster with increasing batch size.
This paper extends Mirror Descent to Riemannian manifolds for optimization.
problem Optimization on Riemannian manifolds.
method Developed a Riemannian Mirror Descent (RMD) framework and a stochastic variant.
result Established non-asymptotic convergence guarantees for RMD and stochastic RMD.
Algorithm improves online canonical correlation analysis.
problem Online canonical correlation analysis.
method Stochastic Scaled-Gradient Descent (SSGD) for minimizing expectation over Riemannian manifolds.
result Achieved optimal one-time-scale algorithm with explicit rate of local asymptotic convergence.
We improve SGD convergence on manifolds using averaging.
problem Minimizing functions on Riemannian manifolds with noisy gradients.
method Developed a geometric framework to transform SGD iterates into an averaged sequence with robust and fast convergence.
result Averaged SGD iterates converge at O(1/n) rate, improving on slow convergence of SGD. Riemannian neural networks outperform standard methods on various datasets.
problem Improving neural network training efficiency and performance.
method Quasi-diagonal Riemannian gradient descent.
result Quasi-diagonal Riemannian algorithms consistently outperform simple stochastic gradient descent.
A new Riemannian algorithm reduces variance in manifold optimization.
problem Optimizing functions on manifolds with stochastic gradient descent.
method Riemannian stochastic variance reduction with retraction and vector transport.
result The proposed algorithm outperforms standard methods on SPD and Grassmann manifolds.
Improved convergence for matrix eigen-decomposition problems.
problem Slow convergence and sub-optimal solutions in matrix eigen-decomposition.
method Deployed variance reduction technique of SGD to Riemannian manifolds.
result Fixed learning rate leads to exponential global convergence rate.
New approach for tensor completion using Riemannian manifold optimization.
problem Tensor completion with rank constraint.
method Riemannian manifold preconditioning approach with novel metric.
result Robust algorithms outperform state-of-the-art across various datasets.
Stochastic Gradient Descent improved for various Hilbert scales and misspecified models.
problem Understanding and optimizing SGD in Hilbert scales for machine learning.
method Extending SGD analysis to Hilbert scales, including Sobolev and Diffusion spaces, and showing the effects of smoothness and preconditioning.
result Violation of smoothness assumption affects learning rate; preconditioning in Hilbert scales reduces the number of iterations for misspecified models.
Stochastic mirror descent improves performance on ensemble models.
problem Improving performance of ensemble models using stochastic mirror descent.
method Utilizes mirror potential to influence training algorithm's implicit bias, mapping evolution to continuous time process.
result Converges to a nonlinear PDE in asymptotic regime of large networks, with mirror potential affecting gradient flow.
A novel Riemannian extension of stochastic variance reduction for manifold optimization.
problem Optimization on the Grassmann manifold for large-scale problems.
method Riemannian stochastic variance reduced gradient (R-SVRG) on the Grassmann manifold.
result The proposed algorithm outperforms standard Riemannian SGD on various problems.
Stochastic gradient descent on manifolds improves low-rank approximation.
problem Efficiently approximate large matrices with lower rank.
method Stochastic gradient descent on a manifold.
result Algorithm outperforms Euclidean space methods on Netflix Prize data.
A new method improves stochastic gradient descent for faster and more efficient estimation.
problem Efficient and fast parametric estimation methods.
method Projected stochastic gradient descent corrected by Fisher scoring.
result The method is faster and more efficient than traditional methods.
Derives Mirror Descent from gradient flow on a Riemannian manifold.
problem No specific problem stated; focuses on derivation.
method Derives Mirror Descent from gradient flow on a Riemannian manifold with a natural discretization.
result Generalizes Mirror Descent to non-Hessian metrics.
The paper introduces a differentially private method for optimization on Riemannian manifolds.
problem Differential privacy in optimization constrained to Riemannian manifolds.
method Adding Gaussian noise to the Riemannian gradient on the tangent space, with privacy and utility guarantees.
result Privacy and utility guarantees for differentially private Riemannian optimization.
New adaptive step-size method for convex optimization without tuning.
problem Optimizing convex functions efficiently with stochastic gradients.
method Adapted Adaptive Gradient Descent Without Descent to stochastic setting.
result Stochastic gradient descent converges under various assumptions.
New adaptive optimization methods for Riemannian manifolds improve training of complex models.
problem Adapting popular adaptive optimization methods to Riemannian manifolds.
method Generalized Adam, Adagrad, and Amsgrad to product Riemannian manifolds.
result Improved convergence and lower train loss on complex embedding tasks.
Gradient descent optimizes deep ReLU networks with proper initialization.
problem Training deep neural networks with ReLU activation.
method Gradient descent and stochastic gradient descent with proper random weight initialization.
result Gradient descent finds global minima for over-parameterized deep ReLU networks.
Kalman Gradient Descent optimizes machine learning models by reducing variance in stochastic optimization.
problem Reducing variance in stochastic gradient descent to improve optimization performance.
method Uses Kalman filtering to adaptively reduce gradient variance in stochastic gradient descent.
result Improved performance on various machine learning tasks including neural networks and black box variational inference.
Improved SGD algorithm with faster convergence.
problem Optimization of machine learning models.
method Conditional accelerated lazy stochastic gradient descent.
result Convergence rate of $O\left(\frac{1}{\varepsilon^2}
ight)$, faster than previous methods.
SGD and stochastic gradient descent converge at optimal rates for certain non-convex functions.
problem Optimal convergence rates for non-convex functions under gradient noise.
method Geometric interpretation of the PL-condition to analyze convergence rates.
result Convergence rates of SGD and stochastic gradient descent match those of strongly convex quadratics.
The paper studies stochastic gradient descent with infinite variance gradients.
problem Theoretical properties of SGD with infinite variance gradients.
method Establish asymptotic behavior of SGD with infinite variance gradients.
result Asymptotic distribution of SGD is characterized as a stationary distribution of an Ornstein-Uhlenbeck process driven by a stable Lévy process.
Information geometry applies concepts in differential geometry to probability and statistics and is especially useful for parameter estimation in exponential families where parameters are known to lie on a Riemannian manifold. Connections between the geometric properties of the induced manifold and statistical properti…
The paper extends gradient flow and relaxation studies to non-flat Riemannian manifolds.
problem Understanding gradient flows and relaxation in non-flat Riemannian manifolds.
method Developed a criterion for comparing relaxation along gradient descent curves using non-metricity tensor.
result Revealed a universal asymmetry: warming up is faster than cooling down.
Gradient descent with delayed updates converges faster with noise, even when delays are significant.
problem Analyzing convergence of gradient descent with delayed gradients and stochastic noise.
method Novel technique using generating functions for convergence analysis.
result Convergence bounds show that stochastic noise mitigates the negative effects of delays, improving performance.
Proof given for SGD convergence in a concise manner.
problem Convergence of Stochastic Gradient Descent (SGD)
method Self-contained proof
result SGD convergence proven
SGD reduces test error by decorrelating updates.
problem Improving generalization error in machine learning models.
method Derive a formula for generalization gap change due to SGD updates, compare to GD, and show decorrelation effect.
result SGD implicitly regularizes generalization error by decorrelating updates.
Improved variance reduction for Riemannian non-convex optimization with adaptive batch size.
problem Optimizing non-convex functions on Riemannian manifolds.
method Batch size adaptation in R-SVRG, R-SRG, and R-SPIDER.
result Achieves lower total complexities for various non-convex functions.
New dynamics for SGD in small learning rate regime.
problem Improving stochastic gradient descent in small learning rate regime.
method Introducing stochastic modified flows and distribution dependent stochastic modified flows.
result Captures fluctuating dynamics of SGD in small learning rate - infinite width scaling regime.
Stochastic gradient descent procedures have gained popularity for parameter estimation from large data sets. However, their statistical properties are not well understood, in theory. And in practice, avoiding numerical instability requires careful tuning of key parameters. Here, we introduce implicit stochastic gradien…
Gradient descent variants improve phase retrieval accuracy.
problem Phase retrieval problem in high-dimensional spaces.
method Gradient descent, stochastic gradient descent, Langevin algorithm, dynamical mean-field theory.
result Stochastic variants of gradient descent achieve better generalization in phase retrieval.
Stochastic Gradient Descent prefers minimizers with flat basins in nonconvex problems.
problem Understanding why SGD prefers minimizers with flat basins in nonconvex problems.
method Detailed analysis of a generic stochastic quadratic problem, deriving a deterministic mechanism.
result Derives a deterministic mechanism explaining why SGD prefers flat minimizers.
SAGD uses Langevin algorithm for efficient gradient descent.
problem Efficiently approximating gradients in complex models.
method Langevin algorithm for biased but asymptotically accurate gradients.
result Theoretical convergence guarantee for SAGD.
New adaptive and accelerated SGD methods achieve optimal convergence rates.
problem Optimizing convergence rates of stochastic gradient descent methods.
method Integrates diagonal scaling and momentum into accelerated SGD.
result Achieves optimal sampling and iteration complexity for smooth stochastic optimization.
Langevin algorithms enhance training of deep neural networks for stochastic control problems.
problem Training acceleration for deep neural networks in stochastic control problems.
method Application of Langevin algorithms to minimize the loss of deep neural networks in stochastic control problems.
result Langevin algorithms improve training on various stochastic control problems.
Stochastic gradient methods converge for training wide PINNs.
problem Convergence of stochastic gradient descent in training over-parameterized PINNs.
method Established linear convergence of stochastic gradient descent/flow in training over-parameterized two-layer PINNs.
result Linear convergence with high probability for general activation functions.
This paper uses antithetic sampling to reduce variance in stochastic gradient descent.
problem High variance in stochastic gradient descent slows down convergence.
method Antithetic sampling to make gradients negatively correlated.
result The proposed method accelerates convergence in machine learning applications.
The paper analyzes stability and generalization of decentralized SGD.
problem Stability and generalization of decentralized stochastic gradient descent.
method Novel formulation of decentralized stochastic gradient descent combined with non/convex optimization theory.
result First stability and generalization guarantees for decentralized stochastic gradient descent.
Improved stochastic gradient descent analysis for non-smooth convex functions.
problem Minimizing non-smooth, non-differentiable convex functions.
method Stochastic gradient descent with suffix averaging method analysis.
result Error rate of final iterate is O(log(T)/T) with high probability. Gradient descent stagnates in low-precision, but unbiased rounding schemes improve convergence.
problem Stagnation of gradient descent in low-precision computation.
method Proposed unbiased stochastic rounding schemes that trade zero bias for larger probability of preserving small gradients.
result Unbiased rounding methods typically improve convergence rate of gradient descent for convex problems.
Stochastic gradient descent approximates Gaussian process posteriors efficiently.
problem Efficiently sampling from Gaussian process posteriors with limited computational resources.
method Developed stochastic gradient optimization objectives for sampling from Gaussian process posteriors.
result Stochastic gradient descent produces accurate predictive distributions, even in non-convergent cases.
Stochastic gradient descent improves Gaussian process regression.
problem Efficiently solving large linear systems in Gaussian process regression.
method Developed a stochastic dual descent algorithm using insights from optimisation and kernel communities.
result Stochastic gradient descent is highly effective when done right.
PSGD accelerates RNN training, achieving competitive performance.
problem Training recurrent neural networks, especially those with long-term memory requirements.
method Preconditioned stochastic gradient descent (PSGD) algorithm.
result PSGD achieves highly competitive performance on RNN training tasks.
Stochastic gradient methods can converge in expectation under heavy-tailed noise.
problem Convergence of stochastic gradient methods under heavy-tailed noise.
method Comprehensive study of stochastic optimization under heavy-tailed noise for extsfSGD, extsfSMD, extsfASMD, extsfSGDM in convex and nonconvex optimization. result Established in-expectation convergence results for various stochastic gradient methods.
SGD fails to converge for deep ReLU networks with limited random initializations.
problem SGD convergence in deep neural networks with limited random initializations.
method Analysis of four discretization parameters: network architecture, training data, gradient steps, and random initializations.
result SGD fails to converge for ReLU networks with depth much larger than width.
This paper shows faster convergence rates for stochastic gradient descent in binary classification.
problem Achieving faster convergence rates for stochastic gradient descent in binary classification.
method Stochastic gradient descent and averaging variant, focusing on exponential convergence rates under strong low-noise conditions.
result Exponential convergence of the expected classification error in the final phase of stochastic gradient descent and averaged stochastic gradient descent for differentiable convex loss functions.