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.

168,694 papers · 148 categories

Trend · papers per month

224447671894 · Jun 202019922001200920172026
48 results for second-order algorithms

Second-order guarantees for federated learning algorithms.

problem Non-convex optimization in federated learning with saddle-points as bottlenecks.
method Drawing on recent results on second-order optimality in centralized and decentralized settings, establish second-order guarantees for federated learning algorithms.
result Established second-order guarantees for federated learning algorithms.

Second-order methods improve differential privacy in convex optimization.

problem Improving differential privacy in convex optimization.
method Developed a private variant of the regularized cubic Newton method for strongly convex loss functions.
result Achieves quadratic convergence and optimal excess loss for strongly convex loss functions.

Two new algorithms improve federated optimization under second-order similarity.

problem Federated learning under communication constraints and second-order similarity.
method SVRP and Catalyzed SVRP algorithms combining proximal point evaluations, client sampling, and variance reduction.
result Achieves superior performance and uniformly improves upon existing algorithms for federated optimization under second-order similarity and strong convexity.

A new method for faster optimization of noisy functions.

problem Optimizing noisy functions efficiently.
method A universal and adaptive second-order method for convex functions.
result Achieves O(σ/T)O(σ/ \sqrt{T}) convergence for stochastic oracles and O(1/T3)O( 1 / T^3) for deterministic oracles.

Optimistic method adapted for faster convex-concave min-max problems.

problem Solving convex-concave min-max optimization problems efficiently.
method Adaptive, line search-free second-order methods combining optimistic updates and second-order information.
result Achieves optimal convergence rate without line search or backtracking.

New algorithms solve complex minimax problems efficiently.

problem Nonconvex-strongly concave minimax problems in machine learning.
method Gradient norm regularized trust-region (GRTR) and Levenberg-Marquardt (LMNegCur) algorithms.
result Proved iteration complexities matching best known results.

AdaSub optimizes with second-order info in low-dims subspace.

problem Efficiently use second-order optimization methods with low computational cost.
method Adaptive subspace selection for second-order optimization.
result AdaSub outperforms other stochastic optimizers in time and iterations.

COMRADE is a communication-efficient, Byzantine-resilient second-order optimization algorithm.

problem Byzantine failures in distributed optimization.
method COMRADE is a communication-efficient, second-order optimization algorithm that uses a simple norm-based thresholding rule to filter out Byzantine workers.
result COMRADE achieves linear-quadratic convergence and is robust against Byzantine workers.

Improved prediction algorithm for 'easy' sequences with reduced regret.

problem Prediction with expert advice for 'easy' sequences.
method Variant of NormalHedge algorithm using second-order εε-quantile regret bound.
result Second-order εε-quantile regret bound of O(VTlog(VT/ε))O\big(\sqrt{V_T \log(V_T/ε)}\big) for VT>logNV_T > \log N.

SONIA optimizes machine learning problems with a novel algorithm.

problem Empirical risk minimization in machine learning.
method Symmetric Blockwise Truncated Optimization (SONIA) algorithm combining second-order and steepest descent steps.
result SONIA converges to stationary points in both convex and nonconvex cases.

Two new algorithms solve nonconvex-strongly concave problems efficiently.

problem Solving nonconvex-strongly concave minimax problems.
method Proposed MINIMAX-TR and MINIMAX-TRACE algorithms.
result Find (ε,ε)(ε, \sqrtε)-second order stationary points within O(ε1.5)\mathcal{O}(ε^{-1.5}) iterations.

New algorithm finds approximate stationary points in non-convex optimization.

problem Finding approximate stationary points in non-convex stochastic optimization.
method Design of an algorithm using O(ε3)O(ε^{-3}) stochastic gradient and Hessian-vector products.
result Optimal rate of O(ε3)O(ε^{-3}) for finding εε-approximate stationary points, matching lower bounds.

Constrained second-order convex optimization algorithms are the method of choice when a high accuracy solution to a problem is needed, due to their local quadratic convergence. These algorithms require the solution of a constrained quadratic subproblem at every iteration. We present the \emph{Second-Order Conditional G…

2020-02-20abs ↗pdf ↗

Finite-sum optimization problems are ubiquitous in machine learning, and are commonly solved using first-order methods which rely on gradient computations. Recently, there has been growing interest in \emph{second-order} methods, which rely on both gradients and Hessians. In principle, second-order methods can require …

2016-11-15abs ↗pdf ↗

Enhances SMC² with Hessian info for more efficient posterior approximation.

problem Improving accuracy and efficiency in Bayesian inference.
method Integrates second-order information (Hessian) into SMC²'s proposal distribution.
result Second-order proposals lead to more accurate posterior approximations and better step-size selection.

AdamQLR optimizes Adam with K-FAC heuristics, achieving comparable performance to tuned benchmarks.

problem Improving the performance of Adam optimizers with stabilizing heuristics.
method Combining Adam's update directions with K-FAC's heuristics (damping and learning rate selection).
result Untuned AdamQLR can achieve comparable performance to tuned benchmarks.

The paper analyzes second-order guarantees for optimization in various architectures.

problem Nonconvex optimization problems are difficult to solve, especially verifying local minima.
method Second-order guarantees for stochastic first-order optimization algorithms in different architectures.
result Gradient perturbations help algorithms distinguish and avoid undesirable stationary points.

AdamNX improves Adam's stability by adjusting its learning rate.

problem Adam's tendency to converge to non-flat minima in large-scale models.
method Proposes a novel exponential decay mechanism for Adam's second-order moment estimate.
result AdamNX outperforms Adam and its variants in stability and performance.

ADAHESSIAN optimizes machine learning models with adaptive second-order methods.

problem Efficiently optimizing machine learning models with second-order methods.
method Dynamic Hessian estimation via adaptive estimates, incorporating fast approximations and moving averages.
result ADAHESSIAN achieves state-of-the-art performance across various tasks.

New algorithm provably converges to second-order stationary points in NMF.

problem Understanding convergence to local minima in NMF.
method Multiplicative weight update dynamics, concurrent updates, and simplex reduction.
result Provable convergence to second-order stationary points.

Second order Sobolev metrics on the space of regular unparametrized planar curves have several desirable completeness properties not present in lower order metrics, but numerics are still largely missing. In this paper, we present algorithms to numerically solve the initial and boundary value problems for geodesics. Th…

2015-07-31abs ↗pdf ↗

New algorithm reduces regret in stochastic bandit convex optimization.

problem Optimizing decisions in uncertain environments with convex losses.
method Introduces a second-order method for zeroth-order stochastic convex bandits.
result Regret bound of (1+r/d)[d1.5n+d3]polylog(n,d,r)(1 + r/d)[d^{1.5} \sqrt{n} + d^3] polylog(n, d, r).

A new algorithm solves minimax problems without needing parameters.

problem Convex-concave minimax optimization problems in machine learning.
method Proposes a fully parameter-free LF-CR and FF-CR algorithms for solving these problems.
result The FF-CR algorithm achieves the best iteration complexity under gradient norm termination criterion.

Paper proposes a new method for efficient second-order neural network training.

problem Infeasibility of Hessian calculation and noisy second-order information in deep learning.
method Adopting complex-step directional derivative (CSFD) for accurate Hessian computation and designing an effective Newton Krylov procedure.
result Our method outperforms existing methods and often converges one-order faster.

Advanced optimization algorithms such as Newton method and AdaGrad benefit from second order derivative or second order statistics to achieve better descent directions and faster convergence rates. At their heart, such algorithms need to compute the inverse or inverse square root of a matrix whose size is quadratic of …

2018-04-16abs ↗pdf ↗

Stein variational gradient descent (SVGD) was recently proposed as a general purpose nonparametric variational inference algorithm [Liu & Wang, NIPS 2016]: it minimizes the Kullback-Leibler divergence between the target distribution and its approximation by implementing a form of functional gradient descent on a reprod…

2018-06-08abs ↗pdf ↗

We aim to design strategies for sequential decision making that adjust to the difficulty of the learning problem. We study this question both in the setting of prediction with expert advice, and for more general combinatorial decision tasks. We are not satisfied with just guaranteeing minimax regret rates, but we want …

2015-02-27abs ↗pdf ↗

Improved Local SGD convergence for general convex objectives with bounded second-order heterogeneity.

problem Understanding when and why Local SGD outperforms alternatives in distributed optimization.
method Established improved convergence guarantees for Local SGD on general convex objectives under bounded second-order heterogeneity.
result Upper bounds for Local SGD are nearly tight, providing a sharper convergence theory.

PDHAMS improves sampling for discrete distributions with quadratic potential functions.

problem Sampling discrete distributions efficiently and accurately.
method Integrates a second-order approximation of the potential function and uses Gaussian integral trick.
result PDHAMS yields superior performance compared to other methods.

Online learning with limited information feedback (bandit) tries to solve the problem where an online learner receives partial feedback information from the environment in the course of learning. Under this setting, Flaxman et al.[8] extended Zinkevich's classical Online Gradient Descent (OGD) algorithm [29] by proposi…

2018-11-25abs ↗pdf ↗

Improved computational complexity in statistical models using second-order information.

problem Polynomial convergence of gradient descent in singular statistical models.
method Normalized Gradient Descent (NormGD) algorithm with second-order information.
result NormGD reaches final statistical radius in logarithmic iterations of nn.