AdaGrad
PulseAugur coverage of AdaGrad — every cluster mentioning AdaGrad across labs, papers, and developer communities, ranked by signal.
-
New adaptive gradient methods enhance AI model training efficiency and generalization · 3 sources tracked
Researchers have developed new adaptive gradient methods to improve the efficiency and generalization of large-scale model training. The first paper introduces AdAdaGrad and AdAdaGradNorm, which progressively increase b…
-
UniDot architecture unifies recommendation models, takes 2nd at KDD Cup 2026
Researchers have developed UniDot, a novel architecture for post-click conversion prediction that unifies feature interaction and sequence modeling. By tokenizing non-sequential features and behavioral sequences into a …
-
AI training efficiency: Gradient optimization methods benchmarked
A new research paper benchmarks five gradient optimizers and three memory strategies for AI training on constrained hardware. The study found that gradient accumulation is the most effective strategy for reducing traini…
-
New study benchmarks gradient optimizers for memory-efficient AI training
A new study benchmarks five gradient optimizers (SGD, Adam, Adagrad, Adadelta, and Conjugate Gradient Descent) against three memory-saving strategies (standard training, gradient checkpointing, and gradient accumulation…
-
New algorithm HT-PAder tackles online convex optimization with heavy-tailed noise
Researchers have developed HT-PAder, a novel parameter-free algorithm designed to tackle online convex optimization challenges in non-stationary environments with heavy-tailed noise. This new approach combines restarted…
-
New ML optimization techniques tackle nonconvex problems and PDE solvers
Researchers have developed new methods for optimizing machine learning algorithms, particularly in the context of nonconvex optimization and scientific computing. One paper introduces a black-box online-to-nonconvex con…
-
AdaGrad optimization scheme shows convergence issues with composite objectives
A new research paper published on arXiv details a limitation of the AdaGrad optimization algorithm when applied to composite objectives. The paper demonstrates a scenario where AdaGrad fails to achieve the expected conv…
-
New continuous-time models for AdaGrad, RMSProp, and Adam
Researchers have developed a continuous-time framework to model popular optimization algorithms like AdaGrad, RMSProp, and Adam. By representing these algorithms as integro-differential equations, the study provides a n…
-
New OptMuon method enhances stochastic optimization with adaptive momentum
Researchers have introduced OptMuon, a novel adaptive momentum orthogonalization method for stochastic nonconvex optimization that calibrates update magnitudes from observed trajectories. This approach combines Muon-sty…
-
Muon optimizer fails on convex Lipschitz functions, study finds
A new paper challenges the theoretical underpinnings of the Muon optimization algorithm, demonstrating that it does not converge on convex Lipschitz functions. The research suggests that Muon's practical success likely …
-
LLM Study Diary #3: PyTorch tensors, float types, and training infrastructure
This LLM study diary entry focuses on PyTorch fundamentals for training large language models. It details tensor basics, exploring various floating-point data types like FP32, BF16, and FP8 for efficiency and stability.…
-
FG^2-GDN enhances long-context understanding with adaptive learning rates
Researchers have introduced FG$^2$-GDN, a novel approach to enhance long-context understanding in neural networks. This method improves upon existing Gated Delta Networks by replacing a scalar learning rate with a chann…
-
New theory unifies adaptive optimization methods for nonconvex machine learning
Researchers have developed a unified framework to analyze first-order optimization algorithms used in nonconvex machine learning. This framework encompasses popular methods like AdaGrad, AdaNorm, and variants of Shampoo…