The separation between training and deployment of machine learning models implies that not all scenarios encountered in deployment can be anticipated during training, and therefore relying solely on advancements in training has its limits. Out-of-distribution (OOD) detection is an important area that stress-tests a model's ability to handle unseen situations: Do models know when they don't know? Existing OOD detection methods either incur extra training steps, additional data or make nontrivial modifications to the trained network. In contrast, in this work, we propose an extremely simple, post-hoc, on-the-fly activation shaping method, ASH, where a large portion (e.g. 90%) of a sample's activation at a late layer is removed, and the rest (e.g. 10%) simplified or lightly adjusted. The shaping is applied at inference time, and does not require any statistics calculated from training data. Experiments show that such a simple treatment enhances in-distribution and out-of-distribution distinction so as to allow state-of-the-art OOD detection on ImageNet, and does not noticeably deteriorate the in-distribution accuracy. Video, animation and code can be found at: https://andrijazz.github.io/ash
InfoQuant: Shaping Activation Distributions for Low-Bit LLM Quantization
School of Software Technology, Zhejiang University(浙江大学软件学院);Ant Group(蚂蚁集团);College of Computer Science and Technology, Zhejiang University of Technology(浙江工业大学计算机科学与技术学院);China Mobile (Zhejiang) Research & Innovation Institute(中国移动(浙江)研究院);Alibaba Cloud Computing(阿里云计算);State Key Lab of CAD&CG, Zhejiang University(浙江大学CAD&CG国家重点实验室)
SPARLING: Learning Latent Representations with Extremely Sparse Activations
Department of Electrical Engineering and Computer Science(电气工程与计算机科学系);Massachusetts Institute of Technology(麻省理工学院);Department of Computer and Information Science(计算机与信息科学系);University of Pennsylvania(宾夕法尼亚大学)
Qronos: Correcting the Past by Shaping the Future... in Post-Training Quantization
Department of Mathematics University of California, San Diego(数学系加州大学圣地亚哥分校);Software Architecture Advanced Micro Devices, Inc.(软件架构先进微器件公司);Department of Mathematics & HDSI University of California, San Diego(数学系及HDSI加州大学圣地亚哥分校)
Neural networks behave as hash encoders: An empirical study
University of Sydney(悉尼大学);University of Science and Technology of China(中国科学技术大学)
The input space of a neural network with ReLU-like activations is partitioned into multiple linear regions, each corresponding to a specific activation pattern of the included ReLU-like activations. We demonstrate that this partition exhibits the following encoding properties across a variety of deep learning models: (1) { \it determinism}: almost every linear region contains at most one training example . We can therefore represent almost every training example by a unique activation pattern, which is parameterized by a { \it neural code}; and (2) { \it categorization}: according to the neura…