no code implementations • 14 Mar 2024 • Heiko Zimmermann, Christian A. Naesseth, Jan-Willem van de Meent
We present variational inference with sequential sample-average approximation (VISA), a method for approximate inference in computationally intensive models, such as those based on numerical simulations.
no code implementations • 15 Feb 2024 • Denis Jered McInerney, William Dickinson, Lucy C. Flynn, Andrea C. Young, Geoffrey S. Young, Jan-Willem van de Meent, Byron C. Wallace
In this work we propose a method to use LLMs to identify pieces of evidence in patient EHR data that indicate increased or decreased risk of specific diagnoses; our ultimate aim is to increase access to evidence and reduce diagnostic errors.
no code implementations • NeurIPS 2023 • Babak Esmaeili, Robin Walters, Heiko Zimmermann, Jan-Willem van de Meent
Incorporating geometric inductive biases into models can aid interpretability and generalization, but encoding to a specific geometric structure can be challenging due to the imposed topological constraints.
no code implementations • 21 Jun 2023 • Ondrej Biza, Skye Thompson, Kishore Reddy Pagidi, Abhinav Kumar, Elise van der Pol, Robin Walters, Thomas Kipf, Jan-Willem van de Meent, Lawson L. S. Wong, Robert Platt
We propose a new method, Interaction Warping, for learning SE(3) robotic manipulation policies from a single demonstration.
no code implementations • 4 May 2023 • Eli Sennesh, Jan-Willem van de Meent
A growing body of research on probabilistic programs and causal models has highlighted the need to reason compositionally about model classes that extend directed graphical models.
no code implementations • 23 Feb 2023 • Denis Jered McInerney, Geoffrey Young, Jan-Willem van de Meent, Byron C. Wallace
We propose CHiLL (Crafting High-Level Latents), an approach for natural-language specification of features for linear models.
1 code implementation • 2 Nov 2022 • James Townsend, Jan-Willem van de Meent
Agda supports formal verification of program properties, and the compiler for our reversible language (which is implemented as an Agda macro), produces not just an encoder/decoder pair of functions but also a proof that they are inverse to one another.
no code implementations • 14 Oct 2022 • Heiko Zimmermann, Fredrik Lindsten, Jan-Willem van de Meent, Christian A. Naesseth
Generative flow networks (GFNs) are a class of models for sequential sampling of composite objects, which approximate a target distribution that is defined in terms of an energy function or a reward.
no code implementations • 12 Oct 2022 • Denis Jered McInerney, Geoffrey Young, Jan-Willem van de Meent, Byron C. Wallace
We compare alignments from a state-of-the-art multimodal (image and text) model for EHR with human annotations that link image regions to sentences.
no code implementations • 22 Aug 2022 • Eli Sennesh, Jordan Theriault, Jan-Willem van de Meent, Lisa Feldman Barrett, Karen Quigley
Active inference offers a principled account of behavior as minimizing average sensory surprise over time.
1 code implementation • 27 Apr 2022 • Ondrej Biza, Robert Platt, Jan-Willem van de Meent, Lawson L. S. Wong, Thomas Kipf
We study the problem of binding actions to objects in object-factored world models using action-attention mechanisms.
1 code implementation • 10 Feb 2022 • Ondrej Biza, Thomas Kipf, David Klee, Robert Platt, Jan-Willem van de Meent, Lawson L. S. Wong
In this paper, we learn to generalize over robotic pick-and-place tasks using object-factored world models, which combat the combinatorial explosion by ensuring that predictions are equivariant to permutations of objects.
2 code implementations • 13 Jan 2022 • Peyman Bateni, Jarred Barber, Raghav Goyal, Vaden Masrani, Jan-Willem van de Meent, Leonid Sigal, Frank Wood
The first method, Simple CNAPS, employs a hierarchically regularized Mahalanobis-distance based classifier combined with a state of the art neural adaptive feature extractor to achieve strong performance on Meta-Dataset, mini-ImageNet and tiered-ImageNet benchmarks.
no code implementations • 29 Sep 2021 • Jung Yeon Park, Ondrej Biza, Linfeng Zhao, Jan-Willem van de Meent, Robin Walters
In this paper, we use equivariant transition models as an inductive bias to learn symmetric latent representations in a self-supervised manner.
no code implementations • ICLR Workshop EBM 2021 • Hao Wu, Babak Esmaeili, Michael Wick, Jean-Baptiste Tristan, Jan-Willem van de Meent
In this paper, we propose conjugate energy-based models (CEBMs), a new class of energy-based models that define a joint density over data and latent variables.
no code implementations • NeurIPS 2021 • Heiko Zimmermann, Hao Wu, Babak Esmaeili, Jan-Willem van de Meent
We develop nested variational inference (NVI), a family of methods that learn proposals for nested importance samplers by minimizing an forward or reverse KL divergence at each level of nesting.
no code implementations • EMNLP 2021 • Xiongyi Zhang, Jan-Willem van de Meent, Byron C. Wallace
Representations from large pretrained models such as BERT encode a range of features into monolithic vectors, affording strong predictive accuracy across a multitude of downstream tasks.
no code implementations • NAACL 2021 • Silvio Amir, Jan-Willem van de Meent, Byron C. Wallace
Recent work has shown that fine-tuning large networks is surprisingly sensitive to changes in random seed(s).
1 code implementation • 1 Mar 2021 • Sam Stites, Heiko Zimmermann, Hao Wu, Eli Sennesh, Jan-Willem van de Meent
Proposals in these samplers can be parameterized using neural networks, which in turn can be trained by optimizing variational objectives.
no code implementations • 22 Feb 2021 • Niklas Smedemark-Margulies, Jung Yeon Park, Max Daniels, Rose Yu, Jan-Willem van de Meent, Paul Hand
We introduce a method for achieving low representation error using generators as signal priors.
1 code implementation • 11 Jan 2021 • Ondrej Biza, Dian Wang, Robert Platt, Jan-Willem van de Meent, Lawson L. S. Wong
This paper proposes an alternative approach where the solutions of previously solved tasks are used to produce an action prior that can facilitate exploration in future tasks.
2 code implementations • 28 Sep 2020 • Peyman Bateni, Jarred Barber, Jan-Willem van de Meent, Frank Wood
We propose a transductive meta-learning method that uses unlabelled instances to improve few-shot image classification performance.
2 code implementations • 17 Jun 2020 • Peyman Bateni, Jarred Barber, Jan-Willem van de Meent, Frank Wood
We develop a transductive meta-learning method that uses unlabelled instances to improve few-shot image classification performance.
Ranked #1 on Few-Shot Image Classification on Tiered ImageNet 10-way (1-shot) (using extra training data)
no code implementations • 9 Apr 2020 • Denis Jered McInerney, Borna Dabiri, Anne-Sophie Touret, Geoffrey Young, Jan-Willem van de Meent, Byron C. Wallace
We propose and evaluate models that extract relevant text snippets from patient records to provide a rough case summary intended to aid physicians considering one or more diagnoses.
1 code implementation • 22 Mar 2020 • Amirreza Farnoosh, Behnaz Rezaei, Eli Zachary Sennesh, Zulqarnain Khan, Jennifer Dy, Ajay Satpute, J. Benjamin Hutchinson, Jan-Willem van de Meent, Sarah Ostadabbas
This results in a flexible family of hierarchical deep generative factor analysis models that can be extended to perform time series clustering or perform factor analysis in the presence of a control signal.
1 code implementation • pproximateinference AABI Symposium 2021 • Ondrej Biza, Robert Platt, Jan-Willem van de Meent, Lawson L. S. Wong
In this work, we propose an information bottleneck method for learning approximate bisimulations, a type of state abstraction.
no code implementations • 11 Nov 2019 • Alican Bozkurt, Babak Esmaeili, Jean-Baptiste Tristan, Dana H. Brooks, Jennifer G. Dy, Jan-Willem van de Meent
Variational autoencoders optimize an objective that combines a reconstruction loss (the distortion) and a KL term (the rate).
1 code implementation • ICML 2020 • Hao Wu, Heiko Zimmermann, Eli Sennesh, Tuan Anh Le, Jan-Willem van de Meent
We develop amortized population Gibbs (APG) samplers, a class of scalable methods that frames structured variational inference as adaptive importance sampling.
no code implementations • NeurIPS 2020 • Eli Sennesh, Zulqarnain Khan, Yiyu Wang, Jennifer Dy, Ajay B. Satpute, J. Benjamin Hutchinson, Jan-Willem van de Meent
Neuroimaging studies produce gigabytes of spatio-temporal data for a small number of participants and stimuli.
1 code implementation • 22 Dec 2018 • Alican Bozkurt, Babak Esmaeili, Dana H. Brooks, Jennifer G. Dy, Jan-Willem van de Meent
This leads to the hypothesis that, for a sufficiently high capacity encoder and decoder, the VAE decoder will perform nearest-neighbor matching according to the coordinates in the latent space.
no code implementations • 12 Dec 2018 • Babak Esmaeili, Hongyi Huang, Byron C. Wallace, Jan-Willem van de Meent
We present Variational Aspect-based Latent Topic Allocation (VALTA), a family of autoencoding topic models that learn aspect-based representations of reviews.
no code implementations • 4 Dec 2018 • Iris Rubi Seaman, Jan-Willem van de Meent, David Wingate
As autonomous agents become more ubiquitous, they will eventually have to reason about the plans of other agents, which is known as theory of mind reasoning.
no code implementations • 14 Nov 2018 • Eli Sennesh, Adam Ścibior, Hao Wu, Jan-Willem van de Meent
We assume that models are dynamic, but that model composition is static, in the sense that combinator application takes place prior to evaluating the model on data.
no code implementations • 31 Oct 2018 • Xiaoyu Lu, Tom Rainforth, Yuan Zhou, Jan-Willem van de Meent, Yee Whye Teh
We study adaptive importance sampling (AIS) as an online learning problem and argue for the importance of the trade-off between exploration and exploitation in this adaptation.
3 code implementations • 27 Sep 2018 • Jan-Willem van de Meent, Brooks Paige, Hongseok Yang, Frank Wood
We start with a discussion of model-based reasoning and explain why conditioning is a foundational computation central to the fields of probabilistic machine learning and artificial intelligence.
no code implementations • 25 Jun 2018 • Tom Rainforth, Yuan Zhou, Xiaoyu Lu, Yee Whye Teh, Frank Wood, Hongseok Yang, Jan-Willem van de Meent
We introduce inference trees (ITs), a new class of inference methods that build on ideas from Monte Carlo tree search to perform adaptive sampling in a manner that balances exploration with exploitation, ensures consistency, and alleviates pathologies in existing adaptive methods.
1 code implementation • EMNLP 2018 • Sarthak Jain, Edward Banner, Jan-Willem van de Meent, Iain J. Marshall, Byron C. Wallace
We propose a method for learning disentangled representations of texts that code for distinct and complementary aspects, with the aim of affording efficient model transfer and interpretability.
no code implementations • 6 Apr 2018 • Babak Esmaeili, Hao Wu, Sarthak Jain, Alican Bozkurt, N. Siddharth, Brooks Paige, Dana H. Brooks, Jennifer Dy, Jan-Willem van de Meent
Deep latent-variable models learn representations of high-dimensional data in an unsupervised manner.
2 code implementations • NeurIPS 2016 • Tom Rainforth, Tuan Anh Le, Jan-Willem van de Meent, Michael A. Osborne, Frank Wood
We present the first general purpose framework for marginal maximum a posteriori estimation of probabilistic program variables.
1 code implementation • NeurIPS 2017 • N. Siddharth, Brooks Paige, Jan-Willem van de Meent, Alban Desmaison, Noah D. Goodman, Pushmeet Kohli, Frank Wood, Philip H. S. Torr
We propose to learn such representations using model architectures that generalise from standard VAEs, employing a general graphical model structure in the encoder and decoder.
no code implementations • 22 Nov 2016 • N. Siddharth, Brooks Paige, Alban Desmaison, Jan-Willem van de Meent, Frank Wood, Noah D. Goodman, Pushmeet Kohli, Philip H. S. Torr
We develop a framework for incorporating structured graphical models in the \emph{encoders} of variational autoencoders (VAEs) that allows us to induce interpretable representations through approximate variational inference.
no code implementations • 21 Nov 2016 • David Janz, Brooks Paige, Tom Rainforth, Jan-Willem van de Meent, Frank Wood
Existing methods for structure discovery in time series data construct interpretable, compositional kernels for Gaussian process regression models.
1 code implementation • 16 Feb 2016 • Tom Rainforth, Christian A. Naesseth, Fredrik Lindsten, Brooks Paige, Jan-Willem van de Meent, Arnaud Doucet, Frank Wood
We introduce interacting particle Markov chain Monte Carlo (iPMCMC), a PMCMC method based on an interacting pool of standard and conditional sequential Monte Carlo samplers.
1 code implementation • 16 Jul 2015 • Jan-Willem van de Meent, Brooks Paige, David Tolpin, Frank Wood
In this work, we explore how probabilistic programs can be used to represent policies in sequential decision problems.
no code implementations • 27 Jan 2015 • Jan-Willem van de Meent, Hongseok Yang, Vikash Mansinghka, Frank Wood
Particle Markov chain Monte Carlo techniques rank among current state-of-the-art methods for probabilistic program inference.
no code implementations • 28 Jan 2014 • Jan-Willem van de Meent, Brooks Paige, Frank Wood
In this paper we demonstrate that tempering Markov chain Monte Carlo samplers for Bayesian models by recursively subsampling observations without replacement can improve the performance of baseline samplers in terms of effective sample size per computation.
no code implementations • 5 Jan 2014 • Amy Rebecca Gansell, Jan-Willem van de Meent, Sakellarios Zairis, Chris H. Wiggins
Thousands of first-millennium BCE ivory carvings have been excavated from Neo-Assyrian sites in Mesopotamia (primarily Nimrud, Khorsabad, and Arslan Tash) hundreds of miles from their Levantine production contexts.
no code implementations • 15 May 2013 • Jan-Willem van de Meent, Jonathan E. Bronson, Frank Wood, Ruben L. Gonzalez Jr., Chris H. Wiggins
We address the problem of analyzing sets of noisy time-varying signals that all report on the same process but confound straightforward analyses due to complex inter-signal heterogeneities and measurement artifacts.