paper-with-me

홈 › Papers

HyperInvariances: Amortizing Invariance Learning

2022-07-17 · Ruchika Chavhan, Henry Gouk, Jan Stühmer, Timothy Hospedales

Providing invariances in a given learning task conveys a key inductive bias that can lead to sample-efficient learning and good generalisation, if correctly specified. However, the ideal invariances for many problems of interest are often not known, which has led both to a body of engineering lore as well as attempts to provide frameworks for invariance learning. However, invariance learning is expensive and data intensive for popular neural architectures. We introduce the notion of amortizing invariance learning. In an up-front learning phase, we learn a low-dimensional manifold of feature extractors spanning invariance to different transformations using a hyper-network. Then, for any problem of interest, both model and invariance learning are rapid and efficient by fitting a low-dimensional invariance descriptor an output head. Empirically, this framework can identify appropriate invariances in different downstream tasks and lead to comparable or better test performance than conventional approaches. Our HyperInvariance framework is also theoretically appealing as it enables generalisation-bounds that provide an interesting new operating point in the trade-off between model fit and complexity.

📄 PDF Abstract BibTeX arXiv:2207.08304

Code (0)

등록된 구현이 없습니다.

Tasks

Inductive Bias

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

Amortized Monte Carlo Integration

2019-07-18 · Adam Goliński, Frank Wood, Tom Rainforth

Current approaches to amortizing Bayesian inference focus solely on approximating the posterior distribution. Typically, this approximation is, in turn, used to calculate expectations for one or more target functions - a…

Bayesian Inference

On Amortizing Inference Cost for Structured Prediction

2012-07-01 · EMNLP 2012 7 · Vivek Srikumar, Gourab Kundu, Dan Roth
Combinatorial OptimizationDependency ParsingPredictionSemantic Role Labeling+1

Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Design

2021-03-03 · Adam Foster, Desi R. Ivanova, Ilyas Malik, Tom Rainforth

We introduce Deep Adaptive Design (DAD), a method for amortizing the cost of adaptive Bayesian experimental design that allows experiments to be run in real-time. Traditional sequential Bayesian optimal experimental desi…

Experimental Design

Amortizing Pragmatic Program Synthesis with Rankings

2024-06-01 · Yewen Pu, Saujas Vaduguru, Priyan Vaithilingam, Elena Glassman 외

The usage of Rational Speech Acts (RSA) framework has been successful in building \emph{pragmatic} program synthesizers that return programs which, in addition to being logically consistent with user-generated examples, …

Program Synthesis

Amortized Inference for Gaussian Process Hyperparameters of Structured Kernels

2023-06-16 · Matthias Bitzer, Mona Meister, Christoph Zimmer

Learning the kernel parameters for Gaussian processes is often the computational bottleneck in applications such as online learning, Bayesian optimization, or active learning. Amortizing parameter inference over differen…

Active LearningBayesian OptimizationGaussian Processes