
Reducing the Variance of Gaussian Process Hyperparameter Optimization with Preconditioning
Gaussian processes remain popular as a flexible and expressive model cla...
read it

Laplace Redux – Effortless Bayesian Deep Learning
Bayesian formulations of deep learning have been shown to have compellin...
read it

Being a Bit Frequentist Improves Bayesian Neural Networks
Despite their compelling theoretical properties, Bayesian neural network...
read it

LinearTime Probabilistic Solutions of Boundary Value Problems
We propose a fast algorithm for the probabilistic solution of boundary v...
read it

ViViT: Curvature access through the generalized GaussNewton's lowrank structure
Curvature in form of the Hessian or its generalized GaussNewton (GGN) a...
read it

Informed Equation Learning
Distilling data into compact and interpretable analytic equations is one...
read it

Laplace Matching for fast Approximate Inference in Generalized Linear Models
Bayesian inference in generalized linear models (GLMs), i.e. Gaussian re...
read it

A Probabilistic State Space Model for Joint Inference from Differential Equations and Data
Mechanistic models with differential equations are a key component of sc...
read it

A Probabilistically Motivated Learning Rate Adaptation for Stochastic Optimization
Machine learning practitioners invest significant manual and computation...
read it

HighDimensional Gaussian Process Inference with Derivatives
Although it is widely known that Gaussian processes can be conditioned o...
read it

Bayesian Quadrature on Riemannian Data Manifolds
Riemannian manifolds provide a principled way to model nonlinear geometr...
read it

Cockpit: A Practical Debugging Tool for Training Deep Neural Networks
When engineers train deep learning models, they are very much "flying bl...
read it

Stable Implementation of Probabilistic ODE Solvers
Probabilistic solvers for ordinary differential equations (ODEs) provide...
read it

Calibrated Adaptive Probabilistic ODE Solvers
Probabilistic solvers for ordinary differential equations (ODEs) assign ...
read it

SelfTuning Stochastic Optimization with CurvatureAware Gradient Filtering
Standard firstorder stochastic optimization algorithms base their updat...
read it

Probabilistic Linear Solvers for Machine Learning
Linear systems are the bedrock of virtually all numerical computation. M...
read it

Robot Learning with Crash Constraints
In the past decade, numerous machine learning algorithms have been shown...
read it

Learnable Uncertainty under Laplace Approximations
Laplace approximations are classic, computationally lightweight means fo...
read it

Fixing Asymptotic Uncertainty of Bayesian Neural Networks with Infinite ReLU Features
Approximate Bayesian methods can mitigate overconfidence in ReLU network...
read it

When are Neural ODE Solutions Proper ODEs?
A key appeal of the recently proposed Neural Ordinary Differential Equat...
read it

Descending through a Crowded Valley – Benchmarking Deep Learning Optimizers
Choosing the optimizer is among the most crucial decisions of deep learn...
read it

Bayesian ODE Solvers: The Maximum A Posteriori Estimate
It has recently been established that the numerical solution of ordinary...
read it

Fast Predictive Uncertainty for Classification with Bayesian Deep Networks
In Bayesian Deep Learning, distributions over the output of classificati...
read it

Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks
The point estimates of ReLU classification networks—arguably the most wi...
read it

Differentiable Likelihoods for Fast Inversion of 'LikelihoodFree' Dynamical Systems
Likelihoodfree (a.k.a. simulationbased) inference problems are inverse...
read it

BackPACK: Packing more into backprop
Automatic differentiation frameworks are optimized for exactly one thing...
read it

Conjugate Gradients for Kernel Machines
Regularized leastsquares (kernelridge / Gaussian process) regression i...
read it

Integrals over Gaussians under Linear Domain Constraints
Integrals of linearly constrained multivariate Gaussian densities are a ...
read it

Classified Regression for Bayesian Optimization: Robot Learning with Unknown Penalties
Learning robot controllers by minimizing a blackbox objective cost usin...
read it

Uncertainty Estimates for Ordinal Embeddings
To investigate objects without a describable notion of distance, one can...
read it

Limitations of the Empirical Fisher Approximation
Natural gradient descent, which preconditions a gradient descent update ...
read it

Convergence Guarantees for Adaptive Bayesian Quadrature Methods
Adaptive Bayesian quadrature (ABQ) is a powerful approach to numerical i...
read it

DeepOBS: A Deep Learning Optimizer Benchmark Suite
Because the choice and tuning of the optimizer affects the speed, and ul...
read it

Active Probabilistic Inference on Matrices for PreConditioning in Stochastic Optimization
Preconditioning is a wellknown concept that can significantly improve ...
read it

A Modular Approach to Blockdiagonal Hessian Approximations for Secondorder Optimization Methods
We propose a modular extension of the backpropagation algorithm for comp...
read it

Fast and Robust Shortest Paths on Manifolds Learned from Data
We propose a fast, simple and robust algorithm for computing shortest pa...
read it

Probabilistic Solutions To Ordinary Differential Equations As NonLinear Bayesian Filtering: A New Perspective
We formulate probabilistic numerical approximations to solutions of ordi...
read it

Probabilistic Linear Solvers: A Unifying View
Several recent works have developed a new, probabilistic interpretation ...
read it

Convergence Rates of Gaussian ODE Filters
A recentlyintroduced class of probabilistic (uncertaintyaware) solvers...
read it

Gaussian Processes and Kernel Methods: A Review on Connections and Equivalences
This paper is an attempt to bridge the conceptual gaps between researche...
read it

Bayesian Filtering for ODEs with Bounded Derivatives
Recently there has been increasing interest in probabilistic solvers for...
read it

On the Design of LQR Kernels for Efficient Controller Learning
Finding optimal feedback controllers for nonlinear dynamic systems from ...
read it

Probabilistic Active Learning of Functions in Structural Causal Models
We consider the problem of learning the functions computing children fro...
read it

Krylov Subspace Recycling for Fast Iterative LeastSquares in Machine Learning
Solving symmetric positive definite linear problems is a fundamental com...
read it

Follow the Signs for Robust Stochastic Optimization
Stochastic noise on gradients is now a common feature in machine learnin...
read it

Probabilistic Line Searches for Stochastic Optimization
In deterministic optimization, line searches are a standard tool ensurin...
read it

Early Stopping without a Validation Set
Early stopping is a widely used technique to prevent poor generalization...
read it

Coupling Adaptive Batch Sizes with Learning Rates
Minibatch stochastic gradient descent and variants thereof have become ...
read it

A probabilistic model for the numerical solution of initial value problems
Like many numerical methods, solvers for initial value problems (IVPs) o...
read it

Exact Sampling from Determinantal Point Processes
Determinantal point processes (DPPs) are an important concept in random ...
read it
Philipp Hennig
is this you? claim profile
Max Planck Research Group Leader at Max Planck Institute for Intelligent Systems