no code implementations • 1 Apr 2024 • Deqing Fu, Ghazal Khalighinejad, Ollie Liu, Bhuwan Dhingra, Dani Yogatama, Robin Jia, Willie Neiswanger
Current foundation models exhibit impressive capabilities when prompted either with text only or with both image and text inputs.
2 code implementations • 13 Feb 2024 • Tailin Wu, Willie Neiswanger, Hongtao Zheng, Stefano Ermon, Jure Leskovec
Deep learning-based surrogate models have demonstrated remarkable advantages over classical solvers in terms of speed, often achieving speedups of 10 to 1000 times over traditional partial differential equation (PDE) solvers.
no code implementations • 4 Feb 2024 • Ollie Liu, Deqing Fu, Dani Yogatama, Willie Neiswanger
Large language models (LLMs) are increasingly used across society, including in domains like business, engineering, and medicine.
1 code implementation • 11 Dec 2023 • Zhengzhong Liu, Aurick Qiao, Willie Neiswanger, Hongyi Wang, Bowen Tan, Tianhua Tao, Junbo Li, Yuqi Wang, Suqi Sun, Omkar Pangarkar, Richard Fan, Yi Gu, Victor Miller, Yonghao Zhuang, Guowei He, Haonan Li, Fajri Koto, Liping Tang, Nikhil Ranjan, Zhiqiang Shen, Xuguang Ren, Roberto Iriondo, Cun Mu, Zhiting Hu, Mark Schulze, Preslav Nakov, Tim Baldwin, Eric P. Xing
The recent surge in open-source Large Language Models (LLMs), such as LLaMA, Falcon, and Mistral, provides diverse options for AI practitioners and researchers.
no code implementations • 1 Dec 2023 • Viraj Mehta, Vikramjeet Das, Ojash Neopane, Yijia Dai, Ilija Bogunovic, Jeff Schneider, Willie Neiswanger
Preference-based feedback is important for many applications in reinforcement learning where direct evaluation of a reward function is not feasible.
no code implementations • 19 Sep 2023 • Zhiqiang Shen, Tianhua Tao, Liqun Ma, Willie Neiswanger, Zhengzhong Liu, Hongyi Wang, Bowen Tan, Joel Hestness, Natalia Vassilieva, Daria Soboleva, Eric Xing
This paper aims to understand the impacts of various data combinations (e. g., web text, wikipedia, github, books) on the training of large language models using SlimPajama.
no code implementations • 21 Jul 2023 • Viraj Mehta, Ojash Neopane, Vikramjeet Das, Sen Lin, Jeff Schneider, Willie Neiswanger
Preference-based feedback is important for many applications where direct evaluation of a reward function is not feasible.
no code implementations • 5 Mar 2023 • Lantao Yu, Tianhe Yu, Jiaming Song, Willie Neiswanger, Stefano Ermon
In this case, a well-known issue is the distribution shift between the learned policy and the behavior policy that collects the offline data.
no code implementations • 19 Dec 2022 • Xiang Li, Viraj Mehta, Johannes Kirschner, Ian Char, Willie Neiswanger, Jeff Schneider, Andreas Krause, Ilija Bogunovic
Many real-world reinforcement learning tasks require control of complex dynamical systems that involve both costly data acquisition processes and large state spaces.
1 code implementation • 10 Oct 2022 • Yuxin Xiao, Paul Pu Liang, Umang Bhatt, Willie Neiswanger, Ruslan Salakhutdinov, Louis-Philippe Morency
In particular, there are various considerations behind the pipeline: (1) the choice and (2) the size of PLM, (3) the choice of uncertainty quantifier, (4) the choice of fine-tuning loss, and many more.
1 code implementation • 7 Oct 2022 • Renbo Tu, Nicholas Roberts, Vishak Prasad, Sibasis Nayak, Paarth Jain, Frederic Sala, Ganesh Ramakrishnan, Ameet Talwalkar, Willie Neiswanger, Colin White
The challenge that climate change poses to humanity has spurred a rapidly developing field of artificial intelligence research focused on climate change applications.
1 code implementation • 6 Oct 2022 • Viraj Mehta, Ian Char, Joseph Abbate, Rory Conlin, Mark D. Boyer, Stefano Ermon, Jeff Schneider, Willie Neiswanger
In this work, we develop a method that allows us to plan for exploration while taking both the task and the current knowledge about the dynamics into account.
no code implementations • 4 Oct 2022 • Willie Neiswanger, Lantao Yu, Shengjia Zhao, Chenlin Meng, Stefano Ermon
Bayesian optimization (BO) is a popular method for efficiently inferring optima of an expensive black-box function via a sequence of queries.
no code implementations • 10 Sep 2022 • Sara A. Miskovich, Willie Neiswanger, William Colocho, Claudio Emma, Jacqueline Garrahan, Timothy Maxwell, Christopher Mayes, Stefano Ermon, Auralee Edelen, Daniel Ratner
Traditional black-box optimizers such as Bayesian optimization are slow and inefficient when dealing with such objectives as they must acquire the full series of measurements, but return only the emittance, with each query.
1 code implementation • 5 Jul 2022 • Sang Keun Choe, Willie Neiswanger, Pengtao Xie, Eric Xing
Gradient-based multilevel optimization (MLO) has gained attention as a framework for studying numerous problems, ranging from hyperparameter optimization and meta-learning to neural architecture search and reinforcement learning.
1 code implementation • 27 Jun 2022 • Jiaming Song, Lantao Yu, Willie Neiswanger, Stefano Ermon
To extend BO to a broader class of models and utilities, we propose likelihood-free BO (LFBO), an approach based on likelihood-free inference.
no code implementations • 23 Jun 2022 • Charles Marx, Shengjia Zhao, Willie Neiswanger, Stefano Ermon
We introduce a versatile class of algorithms for recalibration in regression that we call Modular Conformal Calibration (MCC).
1 code implementation • 22 Mar 2022 • Benedikt Boecking, Nicholas Roberts, Willie Neiswanger, Stefano Ermon, Frederic Sala, Artur Dubrawski
The model outperforms baseline weak supervision label models on a number of multiclass image classification datasets, improves the quality of generated images, and further improves end-model performance through data augmentation with synthetic samples.
1 code implementation • 16 Dec 2021 • Chenlin Meng, Enci Liu, Willie Neiswanger, Jiaming Song, Marshall Burke, David Lobell, Stefano Ermon
We show empirically that the proposed framework achieves strong performance on estimating the number of buildings in the United States and Africa, cars in Kenya, brick kilns in Bangladesh, and swimming pools in the U. S., while requiring as few as 0. 01% of satellite images compared to an exhaustive approach.
1 code implementation • 9 Dec 2021 • Viraj Mehta, Biswajit Paria, Jeff Schneider, Stefano Ermon, Willie Neiswanger
In particular, we leverage ideas from Bayesian optimal experimental design to guide the selection of state-action queries for efficient learning.
2 code implementations • 8 Nov 2021 • Avanika Narayan, Piero Molino, Karan Goel, Willie Neiswanger, Christopher Ré
LBT provides a configurable interface for controlling training and customizing evaluation, a standardized training framework for eliminating confounding variables, and support for multi-objective evaluation.
no code implementations • 29 Sep 2021 • Willie Neiswanger, Lantao Yu, Shengjia Zhao, Chenlin Meng, Stefano Ermon
For special cases of the loss and design space, we develop gradient-based methods to efficiently optimize our proposed family of acquisition functions, and demonstrate that the resulting BO procedure shows strong empirical performance on a diverse set of optimization tasks.
no code implementations • ICLR 2022 • Viraj Mehta, Biswajit Paria, Jeff Schneider, Willie Neiswanger, Stefano Ermon
In particular, we leverage ideas from Bayesian optimal experimental design to guide the selection of state-action queries for efficient learning.
1 code implementation • 21 Sep 2021 • Youngseog Chung, Ian Char, Han Guo, Jeff Schneider, Willie Neiswanger
With increasing deployment of machine learning systems in various real-world tasks, there is a greater need for accurate quantification of predictive uncertainty.
1 code implementation • 23 Jun 2021 • Yang Liu, Sujay Khandagale, Colin White, Willie Neiswanger
In this work, we address this issue by releasing XAI-Bench: a suite of synthetic datasets along with a library for benchmarking feature attribution algorithms.
1 code implementation • 17 Jun 2021 • Yuxin Xiao, Eric P. Xing, Willie Neiswanger
With the surge in the number of hyperparameters and training times of modern machine learning models, hyperparameter tuning is becoming increasingly expensive.
1 code implementation • 19 Apr 2021 • Willie Neiswanger, Ke Alexander Wang, Stefano Ermon
Given such an $\mathcal{A}$, and a prior distribution over $f$, we refer to the problem of inferring the output of $\mathcal{A}$ using $T$ evaluations as Bayesian Algorithm Execution (BAX).
no code implementations • 2 Feb 2021 • Kevin Tran, Willie Neiswanger, Kirby Broderick, Erix Xing, Jeff Schneider, Zachary W. Ulissi
We address this issue by relaxing the catalyst discovery goal into a classification problem: "What is the set of catalysts that is worth testing experimentally?"
Chemical Physics
1 code implementation • ICLR 2021 • Benedikt Boecking, Willie Neiswanger, Eric Xing, Artur Dubrawski
Our experiments demonstrate that only a small number of feedback iterations are needed to train models that achieve highly competitive test set performance without access to ground truth training labels.
2 code implementations • NeurIPS 2021 • Youngseog Chung, Willie Neiswanger, Ian Char, Jeff Schneider
However, this loss restricts the scope of applicable regression models, limits the ability to target many desirable properties (e. g. calibration, sharpness, centered intervals), and may produce poor conditional quantiles.
2 code implementations • 27 Aug 2020 • Aurick Qiao, Sang Keun Choe, Suhas Jayaram Subramanya, Willie Neiswanger, Qirong Ho, Hao Zhang, Gregory R. Ganger, Eric P. Xing
Some recent schedulers choose job resources for users, but do so without awareness of how DL training can be re-optimized to better utilize the provided resources.
2 code implementations • NeurIPS 2020 • Colin White, Willie Neiswanger, Sam Nolen, Yash Savani
First we formally define architecture encodings and give a theoretical characterization on the scalability of the encodings we study Then we identify the main encoding-dependent subroutines which NAS algorithms employ, running experiments to show which encodings work best with each subroutine for many popular algorithms.
no code implementations • 23 Jun 2020 • Viraj Mehta, Ian Char, Willie Neiswanger, Youngseog Chung, Andrew Oakleigh Nelson, Mark D Boyer, Egemen Kolemen, Jeff Schneider
We introduce Neural Dynamical Systems (NDS), a method of learning dynamical models in various gray-box settings which incorporates prior knowledge in the form of systems of ordinary differential equations.
1 code implementation • 12 Jun 2020 • Willie Neiswanger, Aaditya Ramdas
There is a necessary cost to achieving robustness: if the prior was correct, posterior GP bands are narrower than our CS.
no code implementations • ICLR Workshop DeepDiffEq 2019 • Viraj Mehta, Ian Char, Willie Neiswanger, Youngseog Chung, Andrew Oakleigh Nelson, Mark D Boyer, Egemen Kolemen, Jeff Schneider
We introduce Neural Dynamical Systems (NDS), a method of learning dynamical models which incorporates prior knowledge in the form of systems of ordinary differential equations.
no code implementations • 6 Jan 2020 • Youngseog Chung, Ian Char, Willie Neiswanger, Kirthevasan Kandasamy, Andrew Oakleigh Nelson, Mark D Boyer, Egemen Kolemen, Jeff Schneider
One obstacle in utilizing fusion as a feasible energy source is the stability of the reaction.
1 code implementation • 20 Dec 2019 • Kevin Tran, Willie Neiswanger, Junwoong Yoon, Eric Xing, Zachary W. Ulissi
These uncertainty estimates are instrumental for determining which materials to screen next, but there is not yet a standard procedure for judging the quality of such uncertainty estimates objectively.
Materials Science Computational Physics
1 code implementation • NeurIPS 2019 • Ian Char, Youngseog Chung, Willie Neiswanger, Kirthevasan Kandasamy, Oak Nelson, Mark Boyer, Egemen Kolemen
In black-box optimization, an agent repeatedly chooses a configuration to test, so as to find an optimal configuration.
3 code implementations • 25 Oct 2019 • Colin White, Willie Neiswanger, Yash Savani
Bayesian optimization (BO), which has long had success in hyperparameter optimization, has recently emerged as a very promising strategy for NAS when it is coupled with a neural predictor.
no code implementations • 25 Sep 2019 • Colin White, Willie Neiswanger, Yash Savani
We develop a path-based encoding scheme to featurize the neural architectures that are used to train the neural network model.
1 code implementation • 5 Aug 2019 • Ksenia Korovina, Sailun Xu, Kirthevasan Kandasamy, Willie Neiswanger, Barnabas Poczos, Jeff Schneider, Eric P. Xing
In applications such as molecule design or drug discovery, it is desirable to have an algorithm which recommends new candidate molecules based on the results of past tests.
1 code implementation • 15 Mar 2019 • Kirthevasan Kandasamy, Karun Raju Vysyaraju, Willie Neiswanger, Biswajit Paria, Christopher R. Collins, Jeff Schneider, Barnabas Poczos, Eric P. Xing
We compare Dragonfly to a suite of other packages and algorithms for global optimisation and demonstrate that when the above methods are integrated, they enable significant improvements in the performance of BO.
1 code implementation • 31 Jan 2019 • Willie Neiswanger, Kirthevasan Kandasamy, Barnabas Poczos, Jeff Schneider, Eric Xing
Optimizing an expensive-to-query function is a common task in science and engineering, where it is beneficial to keep the number of queries to a minimum.
no code implementations • 10 Jul 2018 • Rajesh Chidambaram, Michael Kampffmeyer, Willie Neiswanger, Xiaodan Liang, Thomas Lachmann, Eric Xing
Analogously, this paper introduces geometric generalization based zero-shot learning tests to measure the rapid learning ability and the internal consistency of deep generative models.
1 code implementation • 25 May 2018 • Kirthevasan Kandasamy, Willie Neiswanger, Reed Zhang, Akshay Krishnamurthy, Jeff Schneider, Barnabas Poczos
We design a new myopic strategy for a wide class of sequential design of experiment (DOE) problems, where the goal is to collect data in order to to fulfil a certain problem specific goal.
1 code implementation • NeurIPS 2018 • Kirthevasan Kandasamy, Willie Neiswanger, Jeff Schneider, Barnabas Poczos, Eric Xing
A common use case for BO in machine learning is model selection, where it is not possible to analytically model the generalisation performance of a statistical model, and we resort to noisy and expensive training and validation procedures to choose the best model.
no code implementations • 8 Mar 2017 • Rebecca C. Steorts, Matt Barnes, Willie Neiswanger
Record linkage involves merging records in large, noisy databases to remove duplicate entities.
no code implementations • ICML 2017 • Willie Neiswanger, Eric Xing
However, we demonstrate that IS will fail for many choices of the target prior, depending on its parametric form and similarity to the false prior.
no code implementations • 14 Oct 2015 • Willie Neiswanger, Chong Wang, Eric Xing
We develop a parallel variational inference (VI) procedure for use in data-distributed settings, where each machine only has access to a subset of data and runs VI independently, without communicating with other machines.
no code implementations • 27 Oct 2014 • Junier Oliva, Willie Neiswanger, Barnabas Poczos, Eric Xing, Jeff Schneider
Function to function regression (FFR) covers a large range of interesting applications including time-series prediction problems, and also more general tasks like studying a mapping between two separate types of distributions.
no code implementations • 22 Sep 2014 • Yu-Xiang Wang, Veeranjaneyulu Sadhanala, Wei Dai, Willie Neiswanger, Suvrit Sra, Eric P. Xing
We develop parallel and distributed Frank-Wolfe algorithms; the former on shared memory machines with mini-batching, and the latter in a delayed update framework.
no code implementations • 19 Nov 2013 • Willie Neiswanger, Chong Wang, Eric Xing
This embarrassingly parallel algorithm allows each machine to act independently on a subset of the data (without communication) until the final combination stage.
no code implementations • 10 Nov 2013 • Junier B. Oliva, Willie Neiswanger, Barnabas Poczos, Jeff Schneider, Eric Xing
We study the problem of distribution to real-value regression, where one aims to regress a mapping $f$ that takes in a distribution input covariate $P\in \mathcal{I}$ (for a non-parametric family of distributions $\mathcal{I}$) and outputs a real-valued response $Y=f(P) + \epsilon$.