BestHub
Sign in
Tagged articles

momentum

6 articles · Page 1 of 1
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Sep 11, 2026 · Artificial Intelligence

Research Like Stock Trading: 40K ICLR Papers Backtest Shows Chasing Hot Topics Works

Analyzing 42,123 ICLR papers (2017–2026) across 28 research directions, the study finds that while hot topics like LLMs grow 60× in three years, their acceptance-rate advantage vanishes at peak popularity; PhD students with short horizons rationally chase momentum, but must check whether growth translates to acceptances or rejections.

GNNICLRLLM
0 likes · 14 min read
Research Like Stock Trading: 40K ICLR Papers Backtest Shows Chasing Hot Topics Works
ZhiKe AI
ZhiKe AI
Jun 26, 2026 · Industry Insights

The Flywheel Effect Explained: Secrets You Didn’t Know

The article breaks down the flywheel effect—why early effort feels futile, how momentum builds through four stages, illustrated by Amazon’s 20‑year growth, and offers three practical steps to keep your own flywheel turning toward lasting success.

AmazonBusiness ManagementFlywheel Effect
0 likes · 9 min read
The Flywheel Effect Explained: Secrets You Didn’t Know
AI Frontier Lectures
AI Frontier Lectures
Mar 21, 2025 · Artificial Intelligence

How ConFIG Eliminates Gradient Conflicts for Faster Multi‑Task Deep Learning

The paper introduces ConFIG (Conflict‑Free Inverse Gradients), a mathematically proven method that resolves gradient conflicts among multiple loss terms in physics‑informed neural networks, multi‑task learning, and continual learning, and its momentum‑based variant M‑ConFIG that further accelerates training while maintaining accuracy.

CONFIGDeep Learning OptimizationGradient Conflict
0 likes · 11 min read
How ConFIG Eliminates Gradient Conflicts for Faster Multi‑Task Deep Learning
Code DAO
Code DAO
Dec 6, 2021 · Artificial Intelligence

Why So Many Optimizers? Core Algorithms Behind Neural Network Training

This article explains the fundamental gradient‑descent optimizers used in neural networks—SGD, Momentum, RMSProp, Adam and their variants—illustrates loss‑surface challenges such as local minima, saddle points and ravines, and shows how techniques like mini‑batching, momentum, adaptive learning rates and scheduling address these issues.

AdamDeep LearningSGD
0 likes · 11 min read
Why So Many Optimizers? Core Algorithms Behind Neural Network Training
Hulu Beijing
Hulu Beijing
Jan 4, 2018 · Artificial Intelligence

Why SGD Fails and How Momentum, AdaGrad, and Adam Fix It

This article explains why vanilla Stochastic Gradient Descent often struggles in deep learning, describes the challenges of valleys and saddle points, and introduces three major SGD variants—Momentum, AdaGrad, and Adam—detailing their motivations, update rules, and advantages.

AdaGradAdamOptimization
0 likes · 13 min read
Why SGD Fails and How Momentum, AdaGrad, and Adam Fix It