paper-with-me

Papers

On Batch Orthogonalization Layers

2018-12-07 · Blanchette, Laganière

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 orthonormalization layers. The performance of the algorithms are compared together with BN with prescribed performance measures.

📄 PDF Abstract BibTeX arXiv:1812.03049

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Spectral Gradient Orthogonalization Improves Differentially Private Training at Scale

2026-08-18 · Sabari Shanmugam, Nick Barnes, Kerry Taylor arxiv

Differentially private training adds isotropic Gaussian noise to clipped gradients, corrupting every singular direction equally. In vision models, where spatial correlation concentrates gradient energy into a low-rank su…

SpecNet2: Orthogonalization-free spectral embedding by neural networks

2022-06-14 · Ziyu Chen, Yingzhou Li, Xiuyuan Cheng

Spectral methods which represent data points by eigenvectors of kernel matrices or graph Laplacian matrices have been a primary tool in unsupervised data analysis. In many application scenarios, parametrizing the spectra…

Computational Efficiency

Pro-KLShampoo: Projected KL-Shampoo with Whitening Recovered by Orthogonalization

2026-05-07 · Ruotong Sun, Ermin Wei arxiv

Optimizers that exploit the matrix structure of gradients are central to modern LLM pre-training, with two distinct frontiers: explicit Kronecker-factored preconditioning -- most recently KL-Shampoo, which estimates the …

Dion3: Full-Stack Orthogonal Updates

2026-08-12 · Noah Amsel, Jack Zhang, Kwangjun Ahn, Ali Naeimi 외 hf

The Muon optimizer incurs a significant overhead cost due to its cubic-time Newton-Schulz orthogonalization step. When weights are sharded, communication overhead compounds this computational cost, eroding the benefits o…

A Unified Batch Selection Policy for Active Metric Learning

2021-02-15 · Priyadarshini K, Siddhartha Chaudhuri, Vivek Borkar, Subhasis Chaudhuri

Active metric learning is the problem of incrementally selecting high-utility batches of training data (typically, ordered triplets) to annotate, in order to progressively improve a learned model of a metric over some in…

Active LearningDiversityInformativenessMetric Learning+1