SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2306.03968 · ICML · 2023

Stochastic Marginal Likelihood Gradients using Neural Tangent Kernels

Gunnar Rätsch, Bernhard Schölkopf, Mark Van Der Wilk, Alexander Immer, Tycho Van Der Ouderaa

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 5 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
AlexImmer/ntk-marglik canonical 2 of 3
aleximmer/ntk-marglik canonical 2 of 2
FunctionStatusWhere it lives
expand_prior_precision Ran AlexImmer/ntk-marglik/ntkmarglik/marglik.py
pointer only (licence: NONE) · get_code("64a6789a3a000193")
get_frame Ran aleximmer/ntk-marglik/generate_illustration_figures.py
pointer only (licence: NONE) · get_code("dc30499117b3d20a")
get_prior_hyperparams Ran AlexImmer/ntk-marglik/ntkmarglik/marglik.py
pointer only (licence: NONE) · get_code("e58f08a5db6faad6")
get_runtime_frame Ran aleximmer/ntk-marglik/generate_illustration_figures.py
pointer only (licence: NONE) · get_code("a11cbf1c7fbeb03b")
valid_performance Not yet run AlexImmer/ntk-marglik/ntkmarglik/marglik.py
pointer only (licence: NONE) · get_code("a8cb194eb229f7e7")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Selecting hyperparameters in deep learning greatly impacts its effectiveness but requires manual effort and expertise. Recent works show that Bayesian model selection with Laplace approximations can allow to optimize such hyperparameters just like standard neural network parameters using gradients and on the training data. However, estimating a single hyperparameter gradient requires a pass through the entire dataset, limiting the scalability of such algorithms. In this work, we overcome this issue by introducing lower bounds to the linearized Laplace approximation of the marginal likelihood. In contrast to previous estimators, these bounds are amenable to stochastic-gradient-based optimization and allow to trade off estimation accuracy against computational complexity. We derive them using the function-space form of the linearized Laplace, which can be estimated using the neural tangent kernel. Experimentally, we show that the estimators can significantly accelerate gradient-based hyperparameter optimization.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2306.03968")
get_code_for_paper("2306.03968")
have("2306.03968")

Connect an agent — have() is free.