Atilim Gunes Baydin — accepted AI-conference papers

2022

Amortized Rejection Sampling in Universal Probabilistic Programming

Saeid Naderiparizi, Adam Scibior, Andreas Munk, Mehrdad Ghadiri, Atilim Gunes Baydin, Bradley J. Gram-Hansen +6

AISTATS 2022poster

Naive approaches to amortized inference in probabilistic programs with unbounded loops can produce estimators with infinite variance. This is particularly true of importance sampling inference in programs that explicitly include rejection sampling as part of the user-programmed generative procedure.…

Cited by 7 Source ↗PDF ↗code ↗Scholar ↗

2022

KL Guided Domain Adaptation

A. Tuan Nguyen, Toan Tran, Yarin Gal, Philip Torr, Atilim Gunes Baydin

ICLR 2022poster

Domain adaptation is an important problem and often needed for real-world applications. In this problem, instead of i.i.d. training and testing datapoints, we assume that the source (training) data and the target (testing) data have different distributions. With that setting, the empirical risk mini…

Cited by 64 Source ↗PDF ↗code ↗Scholar ↗

2021

Domain Invariant Representation Learning with Domain Density Transformations

A. Tuan Nguyen, Toan Tran, Yarin Gal, Atilim Gunes Baydin

NeurIPS 2021poster

Domain generalization refers to the problem where we aim to train a model on data from a set of source domains so that the model can generalize to unseen target domains. Naively training a model on the aggregate set of data (pooled from all source domains) has been shown to perform suboptimally, sin…

Cited by 97 Source ↗PDF ↗code ↗Scholar ↗

2020

Black-Box Optimization with Local Generative Surrogates

Sergey Shirobokov, Vladislav Belavin, Michael Kagan, Andrei Ustyuzhanin, Atilim Gunes Baydin

NeurIPS 2020poster

We propose a novel method for gradient-based optimization of black-box simulators using differentiable local surrogate models. In fields such as physics and engineering, many processes are modeled with non-differentiable simulators with intractable likelihoods. Optimization of these forward models i…

Cited by 75 Source ↗PDF ↗Scholar ↗

2019

Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model

Atilim Gunes Baydin, Lei Shao, Wahid Bhimji, Lukas Heinrich, Saeid Naderiparizi, Andreas Munk +9

NeurIPS 2019poster

We present a novel probabilistic programming framework that couples directly to existing large-scale simulators through a cross-platform probabilistic execution protocol, which allows general-purpose inference engines to record and control random number draws within simulators in a language-agnostic…

Cited by 53 Source ↗PDF ↗code ↗Scholar ↗

2018

Online Learning Rate Adaptation with Hypergradient Descent

Atilim Gunes Baydin, Robert Cornish, David Martinez Rubio, Mark Schmidt, Frank Wood

ICLR 2018poster

We introduce a general method for improving the convergence rate of gradient-based optimizers that is easy to implement and works well in practice. We demonstrate the effectiveness of the method in a range of optimization problems by applying it to stochastic gradient descent, stochastic gradient d…

Cited by 301 Source ↗PDF ↗code ↗Scholar ↗

2017

Inference Compilation and Universal Probabilistic Programming

Tuan Anh Le, Atilim Gunes Baydin, Frank Wood

AISTATS 2017poster

We introduce a method for using deep neural networks to amortize the cost of inference in models from the family induced by universal probabilistic programming languages, establishing a framework that combines the strengths of probabilistic programming and deep learning methods. We call what we do…

Cited by 175 Source ↗PDF ↗Scholar ↗