1 code implementation • 7 Feb 2024 • Andrew Campbell, Jason Yim, Regina Barzilay, Tom Rainforth, Tommi Jaakkola
Our approach achieves state-of-the-art co-design performance while allowing the same multimodal model to be used for flexible generation of the sequence or structure.
1 code implementation • 8 Jan 2024 • Jason Yim, Andrew Campbell, Emile Mathieu, Andrew Y. K. Foong, Michael Gastegger, José Jiménez-Luna, Sarah Lewis, Victor Garcia Satorras, Bastiaan S. Veeling, Frank Noé, Regina Barzilay, Tommi S. Jaakkola
The first is motif amortization, in which FrameFlow is trained with the motif as input using a data augmentation strategy.
no code implementations • 19 Dec 2023 • Simão da Graça Marto, Massimiliano Vasile, Andrew Campbell, Paul Murray, Stephen Marshall, Vasili Savitski
The theoretical and practical aspects of this task are investigated, and the methodology is tested on synthetic data.
no code implementations • 9 Nov 2023 • Andrew Campbell, Hang Liu, Leah Woldemariam, Anna Scaglione
Recent research indicates that frequent model communication stands as a major bottleneck to the efficiency of decentralized machine learning (ML), particularly for large-scale and over-parameterized neural networks (NNs).
1 code implementation • 8 Oct 2023 • Jason Yim, Andrew Campbell, Andrew Y. K. Foong, Michael Gastegger, José Jiménez-Luna, Sarah Lewis, Victor Garcia Satorras, Bastiaan S. Veeling, Regina Barzilay, Tommi Jaakkola, Frank Noé
We present FrameFlow, a method for fast protein backbone generation using SE(3) flow matching.
no code implementations • 14 Aug 2023 • Massimiliano Vasile, Lewis Walker, Andrew Campbell, Simao Marto, Paul Murray, Stephen Marshall, Vasili Savitski
Two techniques are used for material identification and classification: one based on machine learning and the other based on a least square match with a library of known spectra.
no code implementations • 31 May 2023 • Arvind Pillai, Subigya Nepal, Andrew Campbell
Rare life events significantly impact mental health, and their detection in behavioral studies is a crucial step towards health-based interventions.
no code implementations • NeurIPS 2023 • Yuyang Shi, Valentin De Bortoli, Andrew Campbell, Arnaud Doucet
However, while it is desirable in many applications to approximate the deterministic dynamic Optimal Transport (OT) map which admits attractive properties, DDMs and FMMs are not guaranteed to provide transports close to the OT map.
1 code implementation • 26 Jan 2023 • Vincent Stimper, David Liu, Andrew Campbell, Vincent Berenz, Lukas Ryll, Bernhard Schölkopf, José Miguel Hernández-Lobato
It allows to build normalizing flow models from a suite of base distributions, flow layers, and neural networks.
1 code implementation • 30 May 2022 • Andrew Campbell, Joe Benton, Valentin De Bortoli, Tom Rainforth, George Deligiannidis, Arnaud Doucet
We provide the first complete continuous time framework for denoising diffusion models of discrete data.
1 code implementation • NeurIPS 2021 • Andrew Campbell, Yuyang Shi, Tom Rainforth, Arnaud Doucet
We present a variational method for online state estimation and parameter learning in state-space models (SSMs), a ubiquitous class of latent variable models for sequential data.
no code implementations • 25 Jun 2021 • Bishal Lamichhane, Dror Ben-Zeev, Andrew Campbell, Tanzeem Choudhury, Marta Hauser, John Kane, Mikio Obuchi, Emily Scherer, Megan Walsh, Rui Wang, Weichen Wang, Akane Sano
In this work, we investigated a machine learning based schizophrenia relapse prediction model using mobile sensing data to characterize behavioral features.
no code implementations • 22 Jun 2021 • Joanne Zhou, Bishal Lamichhane, Dror Ben-Zeev, Andrew Campbell, Akane Sano
The clustering model based features, together with other features characterizing the mobile sensing data, resulted in an F2 score of 0. 24 for the relapse prediction task in a leave-one-patient-out evaluation setting.
no code implementations • 1 Jan 2021 • Andrew Campbell, Wenlong Chen, Vincent Stimper, José Miguel Hernández-Lobato, Yichuan Zhang
Existing approaches for automating this task either optimise a proxy for mixing speed or consider the HMC chain as an implicit variational distribution and optimize a tractable lower bound that is too loose to be useful in practice.