The paper investigates how single‑hidden‑layer MLPs can fit training data yet fail to recover the underlying rule, focusing on higher‑order interactions and nuisance inputs. Using synthetic parity tasks, the authors benchmark different optimizers (SGD, Adam, Muon) and show that while all achieve perfect accuracy on second‑order interactions, performance drops sharply for higher orders, with Muon outperforming the others at fourth order. Experiments also reveal that freezing or removing nuisance‑related weights dramatically alters training outcomes, highlighting the role of nuisance learning in shaping the rules a shallow network can represent.
By Gongyue Zhang, Honghai Liu
The paper introduces Activation-Keyed Momentum (AK‑Momentum), a momentum update that uses the input activation of a linear layer as a key to apply a delta‑rule update, allowing each direction to decay at a rate proportional to its frequency of appearance. AK‑Momentum is proven to be a valid momentum, incorporates input‑side curvature correction without matrix inversion, and clears stale directions faster than traditional exponential moving average (EMA) under both fixed and drifting optima. It can replace the momentum buffer of any optimizer, scales with width under μP, adds only 22–25% extra compute, and demonstrates significant step‑count reductions in FineWeb‑Edu pretraining and other benchmarks.
whyItMatters":"AK‑Momentum offers a principled, efficient way to adapt momentum decay to anisotropic training dynamics, improving convergence speed and stability across a range of models and datasets."
By Euijin Hong, Guannan Qu
PRIME is a plug‑in residual input‑conditioned mixture of experts that preserves the original dense prediction path while adding low‑rank, input‑dependent logit corrections. By initializing residuals to zero, PRIME matches the baseline dense model at training start and stabilizes conditional estimation with multi‑bag aggregation and EMA load biases. Experiments on Avazu and Criteo across 13 CTR architectures show modest AUC and LogLoss gains, with PRIME outperforming APG on FiBiNET and DCNv2 while using fewer parameters and lower latency.
By Heng Yao, Siyun Hou, Tianying Liu, Yulou Shu, Yong He, Chuan Yuan, Kaibin Qiu, Guowei Chen, Jiayu Zhao, Chao Yu, Ke Ding
arXiv:2607. 06772v1 Announce Type: new Abstract: Learned optimization aims to improve upon hand-designed optimizers (e.
By Xiaolong Huang, Benjamin Th\'erien, James Harrison, Eugene Belilovsky
arXiv:2603. 28921v3 Announce Type: replace-cross Abstract: The critical damping condition of the damped harmonic oscillator model of SGD with momentum (Qian, 1999) yields a momentum schedule with no tuned hyperparameters: mu(t) = 1 - 2*sqrt(alpha(t)).
By Ivan Pasichnyk
arXiv:2411. 16073v4 Announce Type: replace-cross Abstract: Inspired by the Well-initialized Lottery Ticket Hypothesis (WLTH), we introduce Soft-TransFormers (Soft-TF), a continual learning framework that adapts a frozen pre-trained Transformer through task-specific soft subnetworks: real-valued multiplicative masks over the query, key, value, and output projections of selected self-attention layers.
By Haeyong Kang, Chang D. Yoo
Learned optimization aims to improve upon hand-designed optimizers (e. g.
The paper introduces Unmerge, an efficient machine unlearning algorithm that treats unlearning as the inverse of task arithmetic. By representing the forget component as a low‑rank basis at each layer, Unmerge optimizes three goals—matching the merged vector, suppressing leakage, and bounding correction size—to limit forget leakage and retain damage. Experiments on ResNet‑50, ViT‑S/16, and Llama‑3.2‑3B show significant performance gains over existing methods while maintaining privacy and feature‑distribution fidelity.
By Haoran Tang, Andrew Tan, Rajiv Khanna
arXiv:2605.06240v2 Announce Type: replace-cross
Abstract: Forward-Forward (FF) training lets each layer learn from a local goodness criterion. In cumulative-goodness variants, later layers can inheri...
By Amirhossein Yousefiramandi
Neural network pruning reduces model size by removing less important parameters while aiming to preserve predictive performance. Although the Lottery Ticket Hypothesis (LTH) shows that sparse subnetworks can match dense networks when trained from suitable initializations, its iterative pruning procedure requires multiple complete training cycles.
arXiv:2609.18239v1 Announce Type: new
Abstract: Structured pruning is commonly formulated as ranking individual channels, although channel responses can be complementary or cancel through downstream...
By Kaixiang Shu
arXiv:2609. 03241v1 Announce Type: cross Abstract: A reasoning model can improve from its own on-policy experience, but this inner loop is fragile: terminal verifiers provide reliable yet sparse supervision, while dense same-model guidance can reinforce false confidence or overconcentrate learning on a narrow solution mode.
By Zixun Huang, Kishan Panaganti, Haitao Mi, Leowei Liang