924 citations · 4.1k across the 42 of their papers we have counts for
45 papers
AlphaEvolve: A coding agent for scientific and algorithmic discovery
Alexander Novikov, Ngân Vũ, Marvin Eisenberger +15
In this white paper, we present AlphaEvolve, an evolutionary coding agent that substantially enhances capabilities of state-of-the-art LLMs on highly challenging tasks such as tack…
Timewarp: Transferable Acceleration of Molecular Dynamics by Learning Time-Coarsened Dynamics
Leon Klein, Andrew Y. K. Foong, Tor Erlend Fjelde +5
Molecular dynamics (MD) simulation is a widely used technique to simulate molecular systems, most commonly at the all-atom resolution where equations of motion are integrated with…
Efficient data transport over multimode light-pipes with Megapixel images using differentiable ray tracing and Machine-learning
Joowon Lim, Jannes Gladrow, Douglas Kelly +5
Retrieving images transmitted through multi-mode fibers is of growing interest, thanks to their ability to confine and transport light efficiently in a compact system. Here, we dem…
Contextual Squeeze-and-Excitation for Efficient Few-Shot Image Classification
Massimiliano Patacchiola, John Bronskill, Aliaksandra Shysheya +3
Recent years have seen a growth in user-centric applications that require effective knowledge transfer across tasks in the low-data regime. An example is personalization, where a p…
FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification
Aliaksandra Shysheya, John Bronskill, Massimiliano Patacchiola +2
Modern deep learning systems are increasingly deployed in situations such as personalization and federated learning where it is necessary to support i) learning on small amounts of…
Memory Efficient Meta-Learning with Large Images
John Bronskill, Daniela Massiceti, Massimiliano Patacchiola +3
Meta learning approaches to few-shot classification are computationally efficient at test time, requiring just a few optimization steps or single forward pass to learn a new task,…
Precise characterization of the prior predictive distribution of deep ReLU networks
Lorenzo Noci, Gregor Bachmann, Kevin Roth +2
Recent works on Bayesian neural networks (BNNs) have highlighted the need to better understand the implications of using Gaussian priors in combination with the compositional struc…
Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect
Lorenzo Noci, Kevin Roth, Gregor Bachmann +2
The "cold posterior effect" (CPE) in Bayesian deep learning describes the uncomforting observation that the predictive performance of Bayesian neural networks can be significantly…
TaskNorm: Rethinking Batch Normalization for Meta-Learning
John Bronskill, Jonathan Gordon, James Requeima +2
Modern meta-learning approaches for image classification rely on increasingly deep networks to achieve state-of-the-art performance, making batch normalization an essential compone…
The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks
Jakub Swiatkowski, Kevin Roth, Bastiaan S. Veeling +7
Variational Bayesian Inference is a popular methodology for approximating posterior distributions over Bayesian neural network weights. Recent work developing this class of methods…
How Good is the Bayes Posterior in Deep Neural Networks Really?
Florian Wenzel, Kevin Roth, Bastiaan S. Veeling +7
During the past five years the Bayesian deep learning community has developed increasingly accurate and efficient approximate inference procedures that allow for Bayesian inference…
Hydra: Preserving Ensemble Diversity for Model Distillation
Linh Tran, Bastiaan S. Veeling, Kevin Roth +7
Ensembles of models have been empirically shown to improve predictive performance and to yield robust measures of uncertainty. However, they are expensive in computation and memory…
Independent Subspace Analysis for Unsupervised Learning of Disentangled Representations
Jan Stühmer, Richard E. Turner, Sebastian Nowozin
Recently there has been an increased interest in unsupervised learning of disentangled representations using the Variational Autoencoder (VAE) framework. Most of the existing work…
Icebreaker: Element-wise Active Information Acquisition with Bayesian Deep Latent Gaussian Model
Wenbo Gong, Sebastian Tschiatschek, Richard Turner +3
In this paper we introduce the ice-start problem, i.e., the challenge of deploying machine learning models when only little or no training data is initially available, and acquirin…
Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes
James Requeima, Jonathan Gordon, John Bronskill +2
The goal of this paper is to design image classification systems that, after an initial multi-task training phase, can automatically adapt to new tasks encountered at test time. We…
Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift
Yaniv Ovadia, Emily Fertig, Jie Ren +6
Modern machine learning methods including deep learning have achieved great success in predictive accuracy for supervised learning tasks, but may still fall short in giving useful…
Occupancy Networks: Learning 3D Reconstruction in Function Space
Lars Mescheder, Michael Oechsle, Michael Niemeyer +2
With the advent of deep neural networks, learning-based approaches for 3D reconstruction have gained popularity. However, unlike for images, in 3D there is no canonical representat…
Contextual Face Recognition with a Nested-Hierarchical Nonparametric Identity Model
Daniel C. Castro, Sebastian Nowozin
Current face recognition systems typically operate via classification into known identities obtained from supervised identity annotations. There are two problems with this paradigm…
Deterministic Variational Inference for Robust Bayesian Neural Networks
Anqi Wu, Sebastian Nowozin, Edward Meeds +3
Bayesian neural networks (BNNs) hold great promise as a flexible and principled solution to deal with uncertainty when learning from finite data. Among approaches to realize probab…
EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE
Chao Ma, Sebastian Tschiatschek, Konstantina Palla +3
Many real-life decision-making situations allow further relevant information to be acquired at a specific cost, for example, in assessing the health status of a patient we may deci…
From Face Recognition to Models of Identity: A Bayesian Approach to Learning about Unknown Identities from Unsupervised Data
Daniel C. Castro, Sebastian Nowozin
Current face recognition systems robustly recognize identities across a wide variety of imaging conditions. In these systems recognition is performed via classification into known…
Adversarially Robust Training through Structured Gradient Regularization
Kevin Roth, Aurelien Lucchi, Sebastian Nowozin +1
We propose a novel data-dependent structured gradient regularizer to increase the robustness of neural networks vis-a-vis adversarial perturbations. Our regularizer can be derived…
Deep Directional Statistics: Pose Estimation with Uncertainty Quantification
Sergey Prokudin, Peter Gehler, Sebastian Nowozin
Modern deep learning systems successfully solve many perception tasks such as object pose estimation when the input image is of high quality. However, in challenging imaging condit…
Meta-Learning Probabilistic Inference For Prediction
Jonathan Gordon, John Bronskill, Matthias Bauer +2
This paper introduces a new framework for data efficient and versatile learning. Specifically: 1) We develop ML-PIP, a general framework for Meta-Learning approximate Probabilistic…