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.

169,291 papers · 148 categories

Trend · papers per month

54108161215 · May 202619922001200920182026
48 results for acceleration matching

SDM Policy accelerates inference for robotic tasks while maintaining high action quality.

problem Prolonged inference times in diffusion-based policies for high-frequency control tasks.
method Two-stage optimization: score matching and distribution matching; dual-teacher mechanism.
result 6x inference speedup with state-of-the-art action quality.

Paper proves higher-order flow matching preserves optimality in generative modeling.

problem Theoretical guarantees for higher-order flow matching in generative modeling.
method Neural network approximations with controlled depth, width, and sparsity.
result Proves worst case optimality for second-order flow matching.

FMCIT accelerates CI tests for causal discovery, maintaining power and efficiency.

problem High computational complexity in CI tests limits practical applicability of causal discovery methods.
method Flow Matching-based Conditional Independence Test (FMCIT) that leverages flow matching for fast CI tests.
result FMCIT effectively controls type-I error and maintains high testing power under the alternative hypothesis.

ORIGAMI accelerates ML algorithms by splitting compute tasks between in-memory and off-chip accelerators.

problem Memory bandwidth bottleneck in ML processing.
method Heterogeneous in-memory accelerators and off-chip compute platform, pattern-matching for compute patterns, computation-splitting compiler.
result ORIGAMI outperforms state-of-the-art accelerators in performance and energy-efficiency.

New methods accelerate gradient descent for convex and strongly convex functions.

problem Improving convergence rates of gradient-based optimization methods.
method Formulated two classes of first-order algorithms with Lyapunov analyses and Hamiltonian assisted gradient method.
result Achieved accelerated convergence rates matching Nesterov's methods in strongly and general convex settings.

New algorithms accelerate model-based optimization for stochastic problems.

problem Optimizing model-based stochastic optimization problems efficiently.
method Proposed new model-based algorithms with acceleration and minibatch techniques.
result Non-asymptotic convergence guarantees with linear speedup in minibatch size.

GFM models neural network training as a dynamical system to forecast final weights.

problem Computational intensity and inefficiency in training deep neural networks.
method Gradient Flow Matching (GFM) treats training as a dynamical system with learned vector fields.
result GFM achieves forecasting accuracy competitive with Transformer-based models and significantly outperforms classical baselines.

Parallel score matching accelerates DPM training and improves density estimation.

problem Extended training periods and limited modeling flexibility in DPMs.
method Partitioning the learning task into independent time sub-intervals and modeling the score at each time point separately.
result Significant acceleration of training process and improved density estimation performance.

Improved SGD for non-strongly-convex regression with faster convergence.

problem Non-strongly-convex least squares regression problems.
method Modified accelerated gradient descent.
result Achieves optimal prediction error rates of O(d/t)O(d/t) and forgets initial conditions faster to O(d/t2)O(d/t^2).

Unified analysis of matching pursuit and coordinate descent methods.

problem Optimization of linear spaces using first-order methods.
method Unified analysis of matching pursuit and coordinate descent, providing rates for smooth and strongly convex objectives.
result Unified analysis leading to tightest known rates for steepest coordinate descent and accelerated convergence for matching pursuit.

GPU-accelerated particle methods outperform neural samplers in LFT benchmarks.

problem High-dimensional multimodal sampling problems in lattice field theory.
method GPU-accelerated particle Monte Carlo methods (Sequential Monte Carlo and nested sampling).
result These methods match or outperform neural samplers in sample quality and wall-clock time.

Nesterov SGD doesn't accelerate over SGD in over-parameterized learning.

problem Theoretical and practical acceleration of SGD with momentum in over-parameterized learning.
method Introducing a compensation term to Nesterov SGD, resulting in MaSS algorithm.
result MaSS converges for same step sizes as SGD and achieves accelerated convergence rates over SGD.

SuNCEt accelerates contrastive learning with minimal labeled data.

problem Efficiently learning visual representations with limited labeled data.
method Noise-contrastive estimation and neighbourhood component analysis-based semi-supervised loss.
result SuNCEt achieves semi-supervised learning accuracy with less than half the labeled data.

New method solves optimization problems on manifolds using symplectic integrators.

problem Optimization tasks on manifolds with nonlinear constraints.
method Dissipative extension of Dirac's theory of constrained Hamiltonian systems and geometric/symplectic numerical integrators.
result Developed algorithms achieve optimal convergence rates locally.

Paper solves minimax optimization gap with near-optimal algorithms.

problem Designing efficient algorithms for smooth and strongly-convex-strongly-concave minimax problems.
method Accelerated proximal point method and accelerated solver for minimax proximal steps.
result First algorithm with gradient complexity matching the lower bound up to logarithmic factors.

Paper develops a particle filter for rapid model parameter adaptation and change detection.

problem Rapidly adapting to changes in model parameters and distinguishing between regime shifts and stochastic volatility.
method Incorporates genetic algorithm elements into a particle filter for accelerated adaptation and change detection.
result The filter adapts to regime shifts extremely rapidly and provides a clear heuristic for distinguishing between regime shifts and stochastic volatility.

New methods optimize functions on hyperbolic and spherical spaces, matching Euclidean rates up to logarithmic factors.

problem Optimizing functions on non-Euclidean spaces like hyperbolic and spherical geometries.
method Introduced accelerated global first-order methods for LL-smooth and geodesically convex functions on hyperbolic and spherical spaces.
result Achieved the same rates as accelerated gradient descent in Euclidean space, up to logarithmic factors.

Improved first-order algorithm for entropy regularized OT with faster convergence.

problem Solving entropy regularized optimal transport efficiently.
method Accelerated primal-dual stochastic mirror descent algorithm with variance reduction.
result Improved rate from O~(n2.5/ε)\widetilde{O}({n^{2.5}}/ε) to O~(n2/ε)\widetilde{O}({n^2}/ε).

New bounds for online convex optimization between stochastic and adversarial settings.

problem Understanding optimization tasks that are neither i.i.d. nor fully adversarial.
method Establishing novel regret bounds exploiting smoothness of expected losses.
result Regret bounds match expected rates in the fully i.i.d. case and gracefully deteriorate in the fully adversarial case.

Efficiently learns matching rewards in two-sided markets with matrix completion.

problem Learning high-dimensional matching rewards in matching markets with limited data.
method Utilizes matrix completion with a novel approach to handle matching interference.
result Near-optimal guarantees for reward learning under matching interference.

New algorithms improve distributed optimization under specific conditions.

problem Distributed optimization problems with high communication costs.
method SVRS and AccSVRS algorithms combining gradient sliding and variance reduction.
result Achieved better communication complexity in distributed optimization.

New algorithms optimize decentralized convex optimization with near optimal communication and computation.

problem Decentralized convex optimization in large-scale machine learning and sensor networks.
method Novel algorithms combining Nesterov's acceleration, multi-consensus, and gradient-tracking.
result Achieves optimal computation and near optimal communication complexity, matching lower bounds.

New method solves convex optimization faster than NAG.

problem Unconstrained smooth convex optimization problems.
method Accelerated quasi-Newton proximal extragradient (A-QPNE) method.
result Achieves a faster convergence rate of O(min{1k2,dlogkk2.5}){O}\bigl(\min\{\frac{1}{k^2}, \frac{\sqrt{d\log k}}{k^{2.5}}\}\bigr).

Paper accelerates distributed optimization in growing networks.

problem Improving convergence rate of distributed optimization in evolving networks.
method Extending DDA to growing networks, optimizing edge selection and scheduling.
result DDA convergence rate improves with growing network connectivity.

Paper proposes an efficient online Newton method with Nesterov's acceleration for streaming data.

problem Efficient inference of online Newton methods with robustness to noise and ill-conditioning.
method Online Newton method with Hessian averaging and Nesterov's accelerated sketch-and-project solver.
result Global almost-sure convergence and asymptotic normality of the last iterate with non-asymptotic convergence guarantees.

Seesaw optimizes training by balancing learning rate and batch size, accelerating model pretraining.

problem Optimizing training efficiency for large language models with adaptive optimizers.
method Develops a principled framework for batch-size scheduling, introducing Seesaw which multiplies learning rate by 1/√2 and doubles batch size.
result Empirically, Seesaw reduces wall-clock time by approximately 36% compared to cosine decay, matching theoretical limits.

New algorithms improve computation of optimal transport and Wasserstein barycenter.

problem Computing optimal transport and Wasserstein barycenter for multiple probability distributions.
method Introduced APDRCD and APDGCD algorithms for efficient computation, demonstrating better performance than existing methods.
result New algorithms match or exceed the best known complexities for OT problems and improve practical performance.

This paper accelerates gradient methods to find local minima in non-convex optimization.

problem Finding local minima in non-convex optimization problems.
method Polyak's Heavy Ball method and Nesterov's Accelerated Gradient method for extracting negative curvature.
result A new AG algorithm converges to second-order stationary points with improved iteration complexity.

Accelerates pulsar light curve inference with learned representations and optimization.

problem Computational expense of Markov chain Monte Carlo methods for posterior inference.
method Combining U-Net latent representations with local simulator-guided optimization.
result 120x reduction in inference time (24 hours to 12 minutes) with accuracy preserved.

In this paper, we study optimization methods consisting of iteratively minimizing surrogates of an objective function. By proposing several algorithmic variants and simple convergence analyses, we make two main contributions. First, we provide a unified viewpoint for several first-order optimization techniques such as …

2013-05-14abs ↗pdf ↗

DeepRV accelerates spatiotemporal inference using neural priors.

problem Intractable scaling of Gaussian Processes for large datasets.
method Neural-network surrogate replacing GP prior sampling with O(N2)O(N^2) complexity.
result DeepRV achieves highest fidelity to exact GPs while significantly speeding up inference.

New method solves complex optimization problems faster.

problem Minimizing a convex smooth objective over the optimal solution set of another convex smooth problem.
method Uses a cutting plane approach to approximate the lower-level problem and an accelerated gradient method to update the upper-level objective.
result Shows that the method requires at most O(max{1/εf,1/εg})\mathcal{O}(\max\{1/\sqrt{ε_{f}}, 1/ε_g\}) iterations to achieve εfε_f-suboptimality and εgε_g-infeasibility.