arXiv research

Paper discovers structural dynamics equations from only acceleration data.

Accelerates MMLE using SVGD with Nesterov acceleration.

A new method accelerates deep neural network training using minimal margin score.

New study on No-U-Turn Sampler for accelerated mixing in Hamiltonian Monte Carlo.

Derives RL framework for systems without velocity or acceleration measurements.

Utilizing recently introduced concepts from statistics and quantitative risk management, we present a general variant of Batch Normalization (BN) that offers accelerated convergence of Neural Network training compared to conventional BN. In general, we show that mean and standard deviation are not always the most appro…

We formulate gradient-based Markov chain Monte Carlo (MCMC) sampling as optimization on the space of probability measures, with Kullback-Leibler (KL) divergence as the objective functional. We show that an underdamped form of the Langevin algorithm performs accelerated gradient descent in this metric. To characterize t…

Improved reSGLD accelerates convergence in non-convex learning problems.

PTF accelerates RL by reusing source policies without measuring task similarity.

Memory-augmented neural networks (MANNs) are designed for question-answering tasks. It is difficult to run a MANN effectively on accelerators designed for other neural networks (NNs), in particular on mobile devices, because MANNs require recurrent data paths and various types of operations related to external memory a…

Accelerating Magnetic Resonance Imaging (MRI) by taking fewer measurements has the potential to reduce medical costs, minimize stress to patients and make MRI possible in applications where it is currently prohibitively slow or expensive. We introduce the fastMRI dataset, a large-scale collection of both raw MR measure…

Paper proposes a new method to speed up diffusion models.

Paper addresses unsupervised learning from incomplete measurements in inverse problems.

The study characterizes straight-line flows in dynamic measure transport.

Novel geometry-informed irreversible perturbation accelerates Langevin dynamics convergence.

Preconditioned non-convex gradient descent improves noisy matrix estimation.

New algorithm PRACTISE accelerates networks with tiny sets, reducing latency by 22%.

Improved SHB method for faster convergence on strongly-convex quadratics.

ALONE uses neural networks to accelerate cine MRI without needing ground truth.

We provide theoretical complexity analysis for new algorithms to compute the optimal transport (OT) distance between two discrete probability distributions, and demonstrate their favorable practical performance over state-of-art primal-dual algorithms and their capability in solving other problems in large-scale, such …

Study adapts liquidity model to equity auctions, revealing accelerated event rates and reduced price impact.

Sparsity helps reduce the computational complexity of deep neural networks by skipping zeros. Taking advantage of sparsity is listed as a high priority in next generation DNN accelerators such as TPU. The structure of sparsity, i.e., the granularity of pruning, affects the efficiency of hardware accelerator design as w…

Optical scatterometry is a method to measure the size and shape of periodic micro- or nanostructures on surfaces. For this purpose the geometry parameters of the structures are obtained by reproducing experimental measurement results through numerical simulations. We compare the performance of Bayesian optimization to …

Study improves accuracy of risk measures using advanced algorithms.

GADD accelerates uniform-rate discrete diffusion models by 2 orders of magnitude.

Improved KSD test for faster GoF testing.

DRAG decreases regularization to accelerate semi-discrete OT convergence.

Batch normalization has become ubiquitous in many state-of-the-art nets. It accelerates training and yields good performance results. However, there are various other alternatives to normalization, e.g. orthonormalization. The objective of this paper is to explore the possible alternatives to channel normalization with…

This work accelerates constrained sampling using large deviation principles.

Chemical space is so large that brute force searches for new interesting molecules are infeasible. High-throughput virtual screening via computer cluster simulations can speed up the discovery process by collecting very large amounts of data in parallel, e.g., up to hundreds or thousands of parallel measurements. Bayes…

Deep learning architectures (DLA) have shown impressive performance in computer vision, natural language processing and so on. Many DLA make use of cloud computing to achieve classification due to the high computation and memory requirements. Privacy and latency concerns resulting from cloud computing has inspired the …

Accelerates pulsar light curve inference with learned representations and optimization.

New algorithms find near-stationary points in convex optimization.

The study focuses on the experiment of using three different smartphones to collect acceleration data from vibration for the road roughness detection. The Android operating system is used in the application. The study takes place on asphaltic pavement of the expressway system of Thailand, with 9 km distance. The run ve…

Accelerates Riemannian gradient methods with extrapolation.

RFX accelerates and compresses Random Forests for large datasets.

We present several new complexity results for the entropic regularized algorithms that approximately solve the optimal transport (OT) problem between two discrete probability measures with at most $n$ atoms. First, we improve the complexity bound of a greedy variant of Sinkhorn, known as \textit{Greenkhorn}, from $\wid…

Defines SETR to measure carbon transition risk for investors.

Accelerates optimization in asynchronous systems with sparse updates.

Gait event detection of the initial contact and toe off is essential for running gait analysis, allowing the derivation of parameters such as stance time. Heuristic-based methods exist to estimate these key gait events from tibial accelerometry. However, these methods are tailored to very specific acceleration profiles…

We analyze Riemannian accelerated methods using a new framework.

New method improves speed of estimating bivariate functional data.

Super-acceleration of gradient descent with momentum improves loss function minimization.

Unified approach for learning quantum operations from measurements.

PF-LaCG removes the need for knowing smoothness and strong convexity parameters for locally accelerated CG.

Accelerates coordinate descent methods for machine learning problems.

Improves energy efficiency of neuromorphic hardware by optimizing memory organization and encoding schemes.

Continuized Nesterov acceleration accelerates stochastic gradient descent and gossip algorithms.