paper-with-me

홈 › Papers

LSH-SAMPLING BREAKS THE COMPUTATIONAL CHICKEN-AND-EGG LOOP IN ADAPTIVE STOCHASTIC GRADIENT ESTIMATION

2018-01-01 · ICLR 2018 1 · Beidi Chen, Yingchen Xu, Anshumali Shrivastava

Stochastic Gradient Descent or SGD is the most popular optimization algorithm for large-scale problems. SGD estimates the gradient by uniform sampling with sample size one. There have been several other works that suggest faster epoch wise convergence by using weighted non-uniform sampling for better gradient estimates. Unfortunately, the per-iteration cost of maintaining this adaptive distribution for gradient estimation is more than calculating the full gradient. As a result, the false impression of faster convergence in iterations leads to slower convergence in time, which we call a chicken-and-egg loop. In this paper, we break this barrier by providing the first demonstration of a sampling scheme, which leads to superior gradient estimation, while keeping the sampling cost per iteration similar to that of the uniform sampling. Such an algorithm is possible due to the sampling view of Locality Sensitive Hashing (LSH), which came to light recently. As a consequence of superior and fast estimation, we reduce the running time of all existing gradient descent algorithms. We demonstrate the benefits of our proposal on both SGD and AdaGrad.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

AdaGrad AdaGrad is a stochastic optimization method that adapts the learning rate to the parameters. It performs smaller updates for parameters associated with frequently occurring…
SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

Lsh-sampling Breaks the Computation Chicken-and-egg Loop in Adaptive Stochastic Gradient Estimation

2019-10-30 · Beidi Chen, Yingchen Xu, Anshumali Shrivastava

Stochastic Gradient Descent or SGD is the most popular optimization algorithm for large-scale problems. SGD estimates the gradient by uniform sampling with sample size one. There have been several other works that sugges…

On the Interaction Between Chicken Swarm Rejuvenation and KLD-Adaptive Sampling in Particle Filters

2025-11-15 · Hangshuo Tian arxiv

Particle filters (PFs) are often combined with swarm intelligence (SI) algorithms, such as Chicken Swarm Optimization (CSO), for particle rejuvenation. Separately, Kullback--Leibler divergence (KLD) sampling is a common …

Computational Efficiency

Towards Automated Chicken Deboning via Learning-based Dynamically-Adaptive 6-DoF Multi-Material Cutting

2025-10-17 · Zhaodong Yang, Ai-Ping Hu, Harish Ravichandar arxiv

Automating chicken shoulder deboning requires precise 6-DoF cutting through a partially occluded, deformable, multi-material joint, since contact with the bones presents serious health and safety risks. Our work makes bo…

Reinforcement Learning

Fast and Accurate Stochastic Gradient Estimation

2019-12-01 · NeurIPS 2019 12 · Beidi Chen, Yingchen Xu, Anshumali Shrivastava

Stochastic Gradient Descent or SGD is the most popular optimization algorithm for large-scale problems. SGD estimates the gradient by uniform sampling with sample size one. There have been several other works that sugges…

Spatio-temporal stochastic graph-based learning for infectious disease forecasting

2026-05-28 · Luz Stefani Sotomayor Valenzuela, Susanna Cramb, Darren Wraith arxiv

Spatio-temporal graph-based models have typically been used to forecast new cases of infectious diseases such as COVID-19 and chickenpox outbreaks. However, the use of stochastic modelling into their learning process has…