paper-with-me

홈 › Papers

Mimetic Initialization of MLPs

2026-02-06 · Asher Trockman, J. Zico Kolter arxiv

Mimetic initialization uses pretrained models as case studies of good initialization, using observations of structures in trained weights to inspire new, simple initialization techniques. So far, it has been applied only to spatial mixing layers, such convolutional, self-attention, and state space layers. In this work, we present the first attempt to apply the method to channel mixing layers, namely multilayer perceptrons (MLPs). Our extremely simple technique for MLPs -- to give the first layer a nonzero mean -- speeds up training on small-scale vision tasks like CIFAR-10 and ImageNet-1k. Though its effect is much smaller than spatial mixing initializations, it can be used in conjunction with them for an additional positive effect.

📄 PDF Abstract BibTeX arXiv:2602.07156

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Mimetic Initialization of Self-Attention Layers

2023-05-16 · Asher Trockman, J. Zico Kolter

It is notoriously difficult to train Transformers on small datasets; typically, large pre-trained models are instead used as the starting point. We explore the weights of such pre-trained Transformers (particularly for v…

Beyond Periodicity: Towards a Unifying Framework for Activations in Coordinate-MLPs

2021-11-30 · Sameera Ramasinghe, Simon Lucey

Coordinate-MLPs are emerging as an effective tool for modeling multidimensional continuous signals, overcoming many drawbacks associated with discrete grid-based approximations. However, coordinate-MLPs with ReLU activat…

From Universal Approximation Theorem to Tropical Geometry of Multi-Layer Perceptrons

2025-10-16 · Yi-Shan Chu, Yueh-Cheng Kuo arxiv

We revisit the Universal Approximation Theorem(UAT) through the lens of the tropical geometry of neural networks and introduce a constructive, geometry-aware initialization for sigmoidal multi-layer perceptrons (MLPs). T…

Binary Classification

Enhancing the trainability and expressivity of deep MLPs with globally orthogonal initialization

2021-09-27 · NeurIPS Workshop DLDE 2021 12 · Hanwen Wang, Isabelle Crawford-Eng, Paris Perdikaris

Multilayer Perceptrons (MLPs) defines a fundamental model class that forms the backbone of many modern deep learning architectures. Despite their universality guarantees, practical training via stochastic gradient desce…

Mimetic Initialization Helps State Space Models Learn to Recall

2024-10-14 · Asher Trockman, Hrayr Harutyunyan, J. Zico Kolter, Sanjiv Kumar 외

Recent work has shown that state space models such as Mamba are significantly worse than Transformers on recall-based tasks due to the fact that their state size is constant with respect to their input sequence length. B…

MambaState Space Models