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

114229343457 · Jun 202019922001200920172026
48 results for high acceleration

This research accelerates sampling methods using Nesterov's Acceleration.

problem Improving sampling efficiency in MCMC methods.
method Developed a Hessian-Free High-Resolution ODE reformulation of NAG-SC, injected noise, and discretized the diffusion process.
result Quantified acceleration beyond underdamped Langevin in W2W_2 distance for log-strongly-concave targets.

Nested Slice Sampling accelerates Nested Sampling for GPU acceleration.

problem Challenging inference for complex, multimodal targets.
method Vectorized Nested Slice Sampling using Hit-and-Run Slice Sampling.
result NSS maintains accurate evidence estimates and high-quality posterior samples, robust on multimodal problems.

Study accelerates optimization methods in non-convex problems, but doesn't improve the algorithm's performance.

problem Understanding the behavior of momentum-based acceleration methods in non-convex, high-dimensional landscapes.
method Used dynamical mean field theory to describe the average dynamics of heavy-ball momentum and Nesterov acceleration in a non-convex model.
result Accelerated dynamics but did not improve the algorithm's performance with respect to gradient descent.

VegasFlow accelerates complex simulations across various hardware platforms.

problem Complex calculations and simulations requiring high-dimensional integrals.
method Monte Carlo integration techniques using Vegas algorithm and TensorFlow.
result Significantly faster performance on various hardware platforms.

This paper introduces an acceleration structure for hyperbolic embeddings.

problem Efficiently embedding and visualizing high-dimensional data in hyperbolic spaces.
method Building upon a polar quadtree, the paper introduces a new acceleration structure for hyperbolic embeddings.
result The new method computes embeddings in significantly less time compared to existing methods.

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.

Improved sampling for high-dimensional posteriors with underdamped Langevin.

problem Scalability issues in high-dimensional problems with approximate Thompson sampling.
method Underdamped Langevin Monte Carlo for accelerated posterior concentration.
result Logarithmic regret improvement from ildeO(d)\mathcal{ ilde O}(d) to ildeO(d)\mathcal{ ilde O}(\sqrt{d}).

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.

Accelerates MCMC sampling for large-scale problems using machine learning.

problem Efficiently sampling large-scale Bayesian inference problems with high computational cost.
method Integrates low-fidelity machine learning models into a multilevel MCMC framework.
result Significantly accelerates multilevel sampling by a factor of two with similar accuracy.

Hardware-accelerated RBM solves large combinatorial problems and integer factorization.

problem Solving large combinatorial optimization and integer factorization problems.
method Logically synthesized RBM architecture, hardware acceleration, and efficient training methods.
result Hardware-accelerated RBM factorizes 16-bit numbers with 10000x speed and 32x power improvements.

A new method for generating synthetic data using posterior distribution learning accelerates inference.

problem Generating high-quality synthetic data requires many discretization steps, which is computationally expensive.
method Learning the posterior distribution of clean data samples given noisy versions, using a scoring rule instead of regression loss.
result Consistently outperforms standard diffusion models at few discretization steps.

Improved SDE-BNN model reduces NFEs and accelerates convergence.

problem High computational cost and convergence instability in SDE-BNNs.
method Nesterov's Accelerated Gradient (NAG) method integrated into SDE-BNN framework.
result Significantly reduced number of function evaluations (NFEs) and improved predictive accuracy.

RL accelerates portfolio optimization and option pricing by dynamically adjusting preconditioner sizes.

problem Large linear systems in portfolio optimization and option pricing lead to slow convergence.
method Reinforcement Learning (RL) dynamically adjusts block-preconditioner sizes to accelerate convergence.
result RL-driven solver significantly reduces computational cost and accelerates convergence.

New method speeds up diffusion models without requiring complex assumptions.

problem Slow sampling in diffusion models due to high computational cost.
method Training-free acceleration scheme under minimal assumptions.
result Provable acceleration within O~(d5/4/ε)\widetilde{O}(d^{5/4}/\sqrt{\varepsilon}) iterations.

Optimized neural networks for Edge TPU achieve high accuracy in real-time image classification.

problem Designing neural networks for hardware accelerators to achieve optimal performance.
method Hardware-aware neural architecture search and model customization for Edge TPU.
result Improved accuracy-latency tradeoff on Pixel 4's Edge TPU compared to existing models.

New GPU kernels boost deep learning speed and memory efficiency.

problem Sparse deep learning matrices are not well-suited for existing sparse kernels.
method Identified favorable properties of sparse matrices from deep learning, developed high-performance GPU kernels for sparse matrix operations.
result 27% of single-precision peak performance on Nvidia V100 GPUs achieved with new kernels.

This paper introduces Selective-Backprop, a technique that accelerates the training of deep neural networks (DNNs) by prioritizing examples with high loss at each iteration. Selective-Backprop uses the output of a training example's forward pass to decide whether to use that example to compute gradients and update para…

2019-10-02abs ↗pdf ↗

Stella Nera accelerates matrix multiplications with a hash-based approach, achieving high energy efficiency and accuracy.

problem High computational and energy demands due to matrix multiplications in AI models.
method Stella Nera uses Maddness, a hash-based product quantization, to eliminate multipliers and achieve lookups and additions.
result Achieved an energy efficiency of 161 TOp/s/W@0.55V, 25x better than conventional MatMul accelerators.

DeepLight accelerates CTR predictions in ad serving by 46X.

problem Significantly increased serving delay and high memory usage for ad serving.
method Explicitly searching feature interactions, pruning layers, promoting sparsity.
result Accelerates model inference by 46X on Criteo dataset.

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.

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.

LightOn OPUs accelerate randomized numerical linear algebra, reducing computational costs.

problem Computational bottleneck in randomization step for large-scale linear algebra.
method Near constant-time linear random projections from LightOn OPUs.
result Significant acceleration of RandNLA algorithms with negligible precision loss.