A path-norm toolkit for modern networks: consequences, promises and challenges
This work introduces the first toolkit around path-norms that fully encompasses general DAG ReLU networks with biases, skip connections and any operation based on the extraction of order statistics: max pooling, GroupSort etc. This toolkit notably allows us to establish generalization bounds for modern neural networks that are not only the most widely applicable path-norm based ones, but also recover or beat the sharpest known bounds of this type. These extended path-norms further enjoy the usual benefits of path-norms: ease of computation, invariance under the symmetries of the network, and improved sharpness on layered fully-connected networks compared to the product of operator norms, another complexity measure most commonly used. The versatility of the toolkit and its ease of implementation allow us to challenge the concrete promises of path-norm-based generalization bounds, by numerically evaluating the sharpest known bounds for ResNets on ImageNet.
Code (1)
Tasks
Generalization BoundsSimilar Papers 제목 키워드 기반
PySlyde: A Lightweight, Open-Source Toolkit for Pathology Preprocessing
The integration of artificial intelligence (AI) into pathology is advancing precision medicine by improving diagnosis, treatment planning, and patient outcomes. Digitised whole-slide images (WSIs) capture rich spatial an…
Sockeye 2: A Toolkit for Neural Machine Translation
We present Sockeye 2, a modernized and streamlined version of the Sockeye neural machine translation (NMT) toolkit. New features include a simplified code base through the use of MXNet’s Gluon API, a focus on state of th…
Machine TranslationNMTTranslationThe Sockeye 2 Neural Machine Translation Toolkit at AMTA 2020
We present Sockeye 2, a modernized and streamlined version of the Sockeye neural machine translation (NMT) toolkit. New features include a simplified code base through the use of MXNet's Gluon API, a focus on state of th…
CPUMachine TranslationNMTQuantization+1tfp.mcmc: Modern Markov Chain Monte Carlo Tools Built for Modern Hardware
Markov chain Monte Carlo (MCMC) is widely regarded as one of the most important algorithms of the 20th century. Its guarantees of asymptotic convergence, stability, and estimator-variance bounds using only unnormalized p…
Probabilistic ProgrammingGR-NLP-TOOLKIT: An Open-Source NLP Toolkit for Modern Greek
We present GR-NLP-TOOLKIT, an open-source natural language processing (NLP) toolkit developed specifically for modern Greek. The toolkit provides state-of-the-art performance in five core NLP tasks, namely part-of-speech…
Dependency ParsingMorphological Taggingnamed-entity-recognitionNamed Entity Recognition+2