Roberto Bondesan — accepted AI-conference papers

2025

Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Experts

Marta Skreta, Tara Akhound-Sadegh, Viktor Ohanesian, Roberto Bondesan, Alan Aspuru-Guzik, Arnaud Doucet +3

ICML 2025spotlight

While score-based generative models are the model of choice across diverse domains, there are limited tools available for controlling inference-time behavior in a principled manner, e.g. for composing multiple pretrained models. Existing classifier-free guidance methods use a simple heuristic to mix…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗

2023

Neural Simulated Annealing

Alvaro H.C. Correia, Daniel E. Worrall, Roberto Bondesan

AISTATS 2023poster

Simulated annealing (SA) is a stochastic global optimisation metaheuristic applicable to a wide range of discrete and continuous variable problems. Despite its simplicity, SA hinges on carefully handpicked components, viz. proposal distribution and annealing schedule, that often have to be fine tune…

Cited by 19 Source ↗PDF ↗code ↗Scholar ↗

2023

Robust Scheduling with GFlowNets

David W Zhang, Corrado Rainone, Markus Peschl, Roberto Bondesan

ICLR 2023poster

Finding the best way to schedule operations in a computation graph is a classical NP-hard problem which is central to compiler optimization. However, evaluating the goodness of a schedule on the target hardware can be very time-consuming. Traditional approaches as well as previous machine learning o…

Cited by 59 Source ↗PDF ↗Scholar ↗

2022

Batch Bayesian Optimization on Permutations using the Acquisition Weighted Kernel

Changyong Oh, Roberto Bondesan, Efstratios Gavves, Max Welling

NeurIPS 2022accept

In this work we propose a batch Bayesian optimization method for combinatorial problems on permutations, which is well suited for expensive-to-evaluate objectives. We first introduce LAW, an efficient batch acquisition method based on determinantal point processes using the acquisition weighted kern…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗

2022

Neural Topological Ordering for Computation Graphs

Mukul Gagrani, Corrado Rainone, Yang Yang, Harris Teague, Wonseok Jeon, Roberto Bondesan +4

NeurIPS 2022accept

Recent works on machine learning for combinatorial optimization have shown that learning based approaches can outperform heuristic methods in terms of speed and performance. In this paper, we consider the problem of finding an optimal topological order on a directed acyclic graph (DAG) with focus on…

Cited by 13 Source ↗PDF ↗Scholar ↗

2021

Probabilistic Numeric Convolutional Neural Networks

Marc Anton Finzi, Roberto Bondesan, Max Welling

ICLR 2021poster

Continuous input signals like images and time series that are irregularly sampled or have missing values are challenging for existing deep learning methods. Coherently defined feature representations must depend on the values in unobserved regions of the input. Drawing from the work in probabilistic…

Cited by 23 Source ↗PDF ↗Scholar ↗

2021

The Hintons in your Neural Network: a Quantum Field Theory View of Deep Learning

Roberto Bondesan, Max Welling

ICML 2021spotlight

In this work we develop a quantum field theory formalism for deep learning, where input signals are encoded in Gaussian states, a generalization of Gaussian processes which encode the agent’s uncertainty about the input signal. We show how to represent linear and non-linear layers as unitary quantum…

Cited by 8 Source ↗PDF ↗Scholar ↗