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

153305458610 · Jun 202019922001200920172026
48 results for stochastic gradient projection

Optimizes reinsurance and investment strategies to minimize ruin probability.

problem Optimizing reinsurance and investment strategies to minimize ruin probability.
method Stochastic projected gradient method based on Malliavin calculus.
result Effectiveness of the proposed method demonstrated through numerical experiments.

New PG methods tackle nonconvex optimization with auto-conditioned stepsizes.

problem Optimizing nonconvex functions over convex sets.
method Auto-conditioned projected gradient (AC-PG) methods and stochastic variants.
result Achieved optimal iteration complexity for finding approximate stationary points.

New algorithm solves complex optimization problems without needing projections.

problem Optimizing nested functions under convex constraints with noisy evaluations.
method Projection-free conditional gradient-type algorithm for smooth stochastic multi-level composition optimization.
result The algorithm achieves εε-stationary solutions with complexity bounds independent of εε and TT.

In this work we introduce a conditional accelerated lazy stochastic gradient descent algorithm with optimal number of calls to a stochastic first-order oracle and convergence rate O(1ε2)O\left(\frac{1}{\varepsilon^2}\right) improving over the projection-free, Online Frank-Wolfe based stochastic gradient descent of Hazan an…

2017-03-16abs ↗pdf ↗

Paper studies PSGD for constrained optimization problems and its statistical properties.

problem Online inference for constrained optimization problems.
method Stochastic gradient descent with projection (PSGD) for constrained optimization.
result Limiting distribution of PSGD-based estimates under linear-equality constraints.

SMAVE optimizes SDR by projecting onto a low-dimensional subspace on a Riemannian manifold.

problem High-dimensional regression challenges due to the curse of dimensionality.
method SMAVE combines nearest-neighbor localization and Riemannian stochastic gradient ascent.
result SMAVE achieves almost-sure convergence and matches RMAVE's synthetic subspace recovery rate.

Improved convergence for nonconvex optimization with dependent data.

problem Constrained smooth nonconvex optimization with dependent data.
method Stochastic projected gradient methods under a general dependent data sampling scheme.
result Achieved worst-case rate of convergence ildeO(t1/4) ilde{O}(t^{-1/4}) and complexity ildeO(ε4) ilde{O}(\varepsilon^{-4}).

We model how Lipschitz continuity changes during neural network training.

problem Understanding how Lipschitz continuity evolves during training.
method We use a system of stochastic differential equations to capture the dynamics of Lipschitz continuity under SGD.
result We identify three factors driving the evolution of Lipschitz continuity: gradient flow projection, gradient noise, and Hessian projection.

Two algorithms solve nonconvex minimax problems with linear constraints, achieving complexity guarantees.

problem Nonconvex minimax problems with coupled linear constraints.
method Zeroth-order primal-dual alternating projected gradient (ZO-PDAPG) and zeroth-order regularized momentum primal-dual projected gradient (ZO-RMPDPG) algorithms.
result Iteration complexity guarantees for solving nonconvex-(strongly) concave minimax problems with coupled linear constraints.

New projection techniques reduce the frequency of projections in solving LCPs.

problem Solving linearly constrained problems efficiently with reduced projection frequency.
method Delayed projection technique to call a projection less frequently.
result Theoretical and practical improvements in convergence rates and efficiency.

Develops first and second-order pseudo-mirror descent methods for nonnegative function estimation.

problem Nonnegative function estimation in settings like MLE and trajectory optimization.
method First and second-order pseudo-mirror descent with pseudo-gradients and projections.
result Establishes tradeoffs and non-asymptotic bounds on model complexity.

New convergence results for NGVI with various step sizes and sample sizes.

problem Understanding convergence of stochastic NGVI for various schedules.
method Projected stochastic NGVI for exponential family variational distributions.
result Geometric convergence and $\mathcal{O}\left(\frac{1}{T^ρ} ight)$ rates for different schedules.

Algorithm selects public datasets for private machine learning.

problem Choosing the most suitable public dataset for private machine learning.
method Measures gradient subspace distance between public and private datasets.
result Excess risk scales with the subspace distance between gradients.

New guarantees for black-box variational inference methods.

problem Insufficient theoretical guarantees for black-box variational inference.
method Novel convergence guarantees for stochastic optimization of variational inference.
result Provable convergence of proximal and projected stochastic gradient descent for variational inference.

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.

New method estimates SDE parameters efficiently using WCE and SGD.

problem Parameter estimation for stochastic differential equations.
method Wiener Chaos Expansion and Stochastic Gradient Descent.
result Accurate parameter recovery from noisy observations.

Study mini-batch SGD noise and its limits, proving complexity guarantees.

problem Analyzing the noise in mini-batch SGD and its impact on optimization.
method Examined the conditional covariance and diffusion limits of SGD under different sampling designs.
result Proved mean-square upper bounds and Fisher van Trees lower bounds for SGD, linking them to effective dimension and condition number.

BBVI with STL converges geometrically under perfect specification, with quadratic variance bound.

problem Convergence rate of BBVI with STL estimator.
method Proved geometric convergence rate with quadratic variance bound for BBVI with STL estimator.
result BBVI with STL converges geometrically under perfect variational family specification.

Improved neural network training in low-dimensional random bases.

problem Inefficient optimization in large-scale neural networks.
method Re-draw random subspace at each training step, apply independent projections to different network parts.
result Significantly better optimization performance and efficiency.

One of the beauties of the projected gradient descent method lies in its rather simple mechanism and yet stable behavior with inexact, stochastic gradients, which has led to its wide-spread use in many machine learning applications. However, once we replace the projection operator with a simpler linear program, as is d…

2019-10-10abs ↗pdf ↗

GOLS finds activation functions affect training robustness, especially ReLU.

problem Investigate how different activation functions impact GOLS in neural network training.
method Identify SNN-GPPs for GOLS, analyze activation function effects on gradient continuity.
result GOLS robust for most activation functions but sensitive to ReLU.

This work shows neural networks can solve non-convex constraints problems.

problem Training neural networks under non-convex constraints.
method Project stochastic gradient descent with no-regret analysis of online learning.
result Overparameterized neural networks achieve near-optimal and near-feasible solutions.

A new pruning method reduces neural network computation without retraining.

problem Efficiently reduce neural network computation while maintaining accuracy.
method Structured directional pruning via perturbation orthogonal projection.
result Achieves state-of-the-art pruned accuracy without retraining.

A new method solves l1-regularized optimization problems efficiently and sparsely.

problem l1-regularized optimization problems in machine learning.
method Orthant Based Proximal Stochastic Gradient Method (OBProx-SG)
result Promotes sparsity of solutions substantially and converges to global optimal solutions.

New bounds for mixing time and privacy in projected Langevin algorithm and noisy SGD.

problem Analyzing mixing times and privacy in projected Langevin algorithm and noisy SGD.
method New bounds derived using PABI framework and optimization problems.
result New bounds for mixing time and privacy in projected Langevin algorithm and noisy SGD, showing dependency on gradient regularity.

Projective DP-SGD reduces privacy error by identifying low-dimensional gradient subspaces.

problem Differentially private SGD's error rate scales with model's dimensionality, problematic for over-parameterized models.
method Projective DP-SGD, projecting noisy gradients to a low-dimensional subspace identified from a public dataset.
result The method reduces the dependence on model dimensionality, improving accuracy in high privacy regimes.

ODCGM solves non-convex optimization on manifolds with simpler projections.

problem Minimizing non-convex functions over smooth manifolds.
method Orthogonal Directions Constrained Gradient Method (ODCGM) that projects onto a vector space.
result ODCGM converges to the manifold with near-optimal oracle complexities.

The paper analyzes how noise geometry influences the performance of SGD in machine learning.

problem Understanding how noise geometry affects the performance of stochastic gradient descent.
method Developed two metrics to quantify noise alignment strength and analyzed their effects on loss and subspace projection dynamics.
result Noise geometry can be used to guarantee alignment under certain conditions, aiding SGD's ability to escape from sharp minima.

Paper introduces P-FGD for online quantile regression models.

problem Training nonparametric additive quantile regression models in online settings.
method Projected functional gradient descent algorithm (P-FGD) for pinball loss.
result P-FGD achieves minimax optimal consistency rate O(t2s2s+1)O(t^{-\frac{2s}{2s+1}}).

A broad class of convex optimization problems can be formulated as a semidefinite program (SDP), minimization of a convex function over the positive-semidefinite cone subject to some affine constraints. The majority of classical SDP solvers are designed for the deterministic setting where problem data is readily availa…

2019-01-29abs ↗pdf ↗

Accelerates Birkhoff projection for manifold-constrained hyper-connections with high accuracy and speed.

problem Inaccurate and slow Birkhoff projection in mHC implementations.
method Dual formulation, Newton's method, implicit differentiation, warp-level CUDA kernel.
result Substantial speedups and accuracy improvements in doubly stochastic projections.

Stochastic optimization of continuous objectives is at the heart of modern machine learning. However, many important problems are of discrete nature and often involve submodular objectives. We seek to unleash the power of stochastic continuous optimization, namely stochastic gradient descent and its variants, to such d…

2017-11-05abs ↗pdf ↗

Two new Frank-Wolfe algorithms improve convergence for constrained optimization.

problem Solving optimization problems with structured constraints in machine learning.
method Two new variants of the Frank-Wolfe (FW) method for stochastic finite-sum minimization.
result Best convergence guarantees for convex and non-convex objective functions.