34 citations · 108 across the 30 of their papers we have counts for
33 papers
Work While They Sleep: Exploiting Evaluation Latency for Fully Bayesian Optimization
Gustavo Sutter, Alejandro Comas-Leon, David Holzmüller +4
Black-box optimization problems are ubiquitous across science and engineering, often dealing with expensive objective functions. This objective latency has two consequences during…
Out-Of-The-Loop Multi-Fidelity Bayesian Optimization
Gustavo Sutter, Hao Wang, Luis Ricardez-Sandoval +2
Black-box optimization is a ubiquitous problem in science and engineering, often dealing with expensive objective functions with cheaper lower-fidelity proxies available. Multi-fid…
Benchmarking Instance-Dependent Label Noise with Controlled Corruptions
Shadman Islam, Agustinus Kristiadi, Mostafa Milani
Synthetic instance-dependent label noise (IDN) benchmarks are widely used to evaluate noisy-label learning methods, yet existing approaches typically generate noise through imperfe…
Limits of PRM-Guided Tree Search for Mathematical Reasoning with LLMs
Tristan Cinquin, Geoff Pleiss, Agustinus Kristiadi
While chain-of-thought prompting with Best-of-N (BoN) selection has become popular for mathematical reasoning in large language models (LLMs), its linear structure fails to capture…
Introduction to the Analysis of Probabilistic Decision-Making Algorithms
Agustinus Kristiadi
Decision theories offer principled methods for making choices under various types of uncertainty. Algorithms that implement these theories have been successfully applied to a wide…
Simplifying Bayesian Optimization Via In-Context Direct Optimum Sampling
Gustavo Sutter Pessurno de Carvalho, Mohammed Abdulrahman, Hao Wang +7
The optimization of expensive black-box functions is ubiquitous in science and engineering. A common solution to this problem is Bayesian optimization (BO), which is generally comp…
FlashMD: long-stride, universal prediction of molecular dynamics
Filippo Bigi, Sanggyu Chong, Agustinus Kristiadi +1
Molecular dynamics (MD) provides insights into atomic-scale processes by integrating over time the equations that describe the motion of atoms under the action of interatomic force…
Bayesian Optimization for General Reaction Conditions
Stefan P. Schmid, Ella Miray Rajaonson, Cher Tian Ser +6
General chemical reaction conditions that achieve consistently high performance across multiple substrates are important for practical applications such as library synthesis and hi…
Towards Cost-Effective Reward Guided Text Generation
Ahmad Rashid, Ruotian Wu, Rongqi Fan +3
Reward-guided text generation (RGTG) has emerged as a viable alternative to offline reinforcement learning from human feedback (RLHF). RGTG methods can align baseline language mode…
Position: Curvature Matrices Should Be Democratized via Linear Operators
Felix Dangel, Runa Eschenhagen, Weronika Ormaniec +3
Structured large matrices are prevalent in machine learning. A particularly important class is curvature matrices like the Hessian, which are central to understanding the loss land…
Low-Rank Filtering and Smoothing for Sequential Deep Learning
Joanna Sliwa, Frank Schneider, Nathanael Bosch +2
Learning multiple tasks sequentially requires neural networks to balance retaining knowledge, yet being flexible enough to adapt to new tasks. Regularizing network parameters is a…
Uncertainty-Guided Likelihood Tree Search
Julia Grosse, Ruotian Wu, Ahmad Rashid +4
Tree search is a fundamental tool for planning, as many sequential decision-making problems can be framed as searching over tree-structured spaces. We propose an uncertainty-guided…
How Useful is Intermittent, Asynchronous Expert Feedback for Bayesian Optimization?
Agustinus Kristiadi, Felix Strieth-Kalthoff, Sriram Ganapathi Subramanian +3
Bayesian optimization (BO) is an integral part of automated scientific discovery -- the so-called self-driving lab -- where human inputs are ideally minimal or at least non-blockin…
A Critical Look At Tokenwise Reward-Guided Text Generation
Ahmad Rashid, Ruotian Wu, Julia Grosse +2
Large language models (LLMs) can be improved by aligning with human preferences through fine-tuning -- the so-called reinforcement learning from human feedback (RLHF). However, the…
A Sober Look at LLMs for Material Discovery: Are They Actually Good for Bayesian Optimization Over Molecules?
Agustinus Kristiadi, Felix Strieth-Kalthoff, Marta Skreta +3
Automation is one of the cornerstones of contemporary material discovery. Bayesian optimization (BO) is an essential part of such workflows, enabling scientists to leverage prior d…
Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI
Theodore Papamarkou, Maria Skoularidou, Konstantina Palla +22
In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language dat…
Structured Inverse-Free Natural Gradient: Memory-Efficient & Numerically-Stable KFAC
Wu Lin, Felix Dangel, Runa Eschenhagen +4
Second-order methods such as KFAC can be useful for neural net training. However, they are often memory-inefficient since their preconditioning Kronecker factors are dense, and num…
Preventing Arbitrarily High Confidence on Far-Away Data in Point-Estimated Discriminative Neural Networks
Ahmad Rashid, Serena Hacker, Guojun Zhang +2
Discriminatively trained, deterministic neural networks are the de facto choice for classification problems. However, even though they achieve state-of-the-art results on in-domain…
On the Disconnect Between Theory and Practice of Neural Networks: Limits of the NTK Perspective
Jonathan Wenger, Felix Dangel, Agustinus Kristiadi
The neural tangent kernel (NTK) has garnered significant attention as a theoretical framework for describing the behavior of large-scale neural networks. Kernel methods are theoret…
Promises and Pitfalls of the Linearized Laplace in Bayesian Optimization
Agustinus Kristiadi, Alexander Immer, Runa Eschenhagen +1
The linearized-Laplace approximation (LLA) has been shown to be effective and efficient in constructing Bayesian neural networks. It is theoretically compelling since it can be see…
The Geometry of Neural Nets' Parameter Spaces Under Reparametrization
Agustinus Kristiadi, Felix Dangel, Philipp Hennig
Model reparametrization, which follows the change-of-variable rule of calculus, is a popular way to improve the training of neural nets. But it can also be problematic since it can…
Posterior Refinement Improves Sample Efficiency in Bayesian Neural Networks
Agustinus Kristiadi, Runa Eschenhagen, Philipp Hennig
Monte Carlo (MC) integration is the de facto method for approximating the predictive distribution of Bayesian neural networks (BNNs). But, even with many MC samples, Gaussian-based…
Discovering Inductive Bias with Gibbs Priors: A Diagnostic Tool for Approximate Bayesian Inference
Luca Rendsburg, Agustinus Kristiadi, Philipp Hennig +1
Full Bayesian posteriors are rarely analytically tractable, which is why real-world Bayesian inference heavily relies on approximate techniques. Approximations generally differ fro…
Mixtures of Laplace Approximations for Improved Post-Hoc Uncertainty in Deep Learning
Runa Eschenhagen, Erik Daxberger, Philipp Hennig +1
Deep neural networks are prone to overconfident predictions on outliers. Bayesian neural networks and deep ensembles have both been shown to mitigate this problem to some extent. I…