1 code implementation • 5 Mar 2024 • Yair Schiff, Chia-Hsiang Kao, Aaron Gokaslan, Tri Dao, Albert Gu, Volodymyr Kuleshov
Large-scale sequence modeling has sparked rapid advances that now extend into biology and genomics.
1 code implementation • 6 Feb 2024 • Albert Tseng, Jerry Chee, Qingyao Sun, Volodymyr Kuleshov, Christopher De Sa
Second, QuIP# uses vector quantization techniques to take advantage of the ball-shaped sub-Gaussian distribution that incoherent weights possess: specifically, we introduce a set of hardware-efficient codebooks based on the highly symmetric $E_8$ lattice, which achieves the optimal 8-dimension unit ball packing.
no code implementations • 6 Feb 2024 • Yair Schiff, Zhong Yi Wan, Jeffrey B. Parker, Stephan Hoyer, Volodymyr Kuleshov, Fei Sha, Leonardo Zepeda-Núñez
Learning dynamics from dissipative chaotic systems is notoriously difficult due to their inherent instability, as formalized by their positive Lyapunov exponents, which exponentially amplify errors in the learned dynamics.
no code implementations • 5 Jan 2024 • Top Piriyakulkij, Yingheng Wang, Volodymyr Kuleshov
We propose denoising diffusion variational inference (DDVI), an approximate inference algorithm for latent variable models which relies on diffusion models as flexible variational posteriors.
1 code implementation • 20 Dec 2023 • Subham Sekhar Sahoo, Aaron Gokaslan, Chris De Sa, Volodymyr Kuleshov
Diffusion models have gained traction as powerful algorithms for synthesizing high-quality images.
Ranked #1 on Density Estimation on ImageNet 32x32
no code implementations • 19 Dec 2023 • Top Piriyakulkij, Volodymyr Kuleshov, Kevin Ellis
To enable this ability for instruction-tuned large language models (LLMs), one may prompt them to ask users questions to infer their preferences, transforming the language models into more robust, interactive systems.
1 code implementation • 25 Oct 2023 • Aaron Gokaslan, A. Feder Cooper, Jasmine Collins, Landan Seguin, Austin Jacobson, Mihir Patel, Jonathan Frankle, Cory Stephenson, Volodymyr Kuleshov
This task presents two challenges: (1) high-resolution CC images lack the captions necessary to train text-to-image generative models; (2) CC images are relatively scarce.
no code implementations • 25 Oct 2023 • Jacqueline Maasch, Weishen Pan, Shantanu Gupta, Volodymyr Kuleshov, Kyra Gan, Fei Wang
Causal discovery is crucial for causal inference in observational studies: it can enable the identification of valid adjustment sets (VAS) for unbiased effect estimation.
1 code implementation • 10 Oct 2023 • John X. Morris, Volodymyr Kuleshov, Vitaly Shmatikov, Alexander M. Rush
How much private information do text embeddings reveal about the original text?
3 code implementations • 28 Sep 2023 • Junjie Yin, Jiahao Dong, Yingheng Wang, Christopher De Sa, Volodymyr Kuleshov
We propose a memory-efficient finetuning algorithm for large language models (LLMs) that supports finetuning LLMs with 65B parameters in 2/3/4-bit precision on as little as one 24GB GPU.
1 code implementation • NeurIPS 2023 • Jerry Chee, Yaohui Cai, Volodymyr Kuleshov, Christopher De Sa
This work studies post-training parameter quantization in large language models (LLMs).
no code implementations • 14 Jun 2023 • Yingheng Wang, Yair Schiff, Aaron Gokaslan, Weishen Pan, Fei Wang, Christopher De Sa, Volodymyr Kuleshov
While diffusion models excel at generating high-quality samples, their latent variables typically lack semantic meaning and are not suitable for representation learning.
no code implementations • 1 Jun 2023 • Shachi Deshpande, Volodymyr Kuleshov
Propensity scores are commonly used to balance observed covariates while estimating treatment effects.
no code implementations • 23 Feb 2023 • Volodymyr Kuleshov, Shachi Deshpande
Accurately estimating uncertainty is an essential component of decision-making and forecasting in machine learning.
no code implementations • 17 Oct 2022 • Jacqueline R. M. A. Maasch, Hao Zhang, Qian Yang, Fei Wang, Volodymyr Kuleshov
The cost of manual data labeling can be a significant obstacle in supervised learning.
1 code implementation • 16 Oct 2022 • Yuntian Deng, Volodymyr Kuleshov, Alexander M. Rush
Language models have demonstrated the ability to generate highly fluent text; however, it remains unclear whether their output retains coherent high-level structure (e. g., story progression).
no code implementations • 14 Jun 2022 • Phillip Si, Zeyi Chen, Subham Sekhar Sahoo, Yair Schiff, Volodymyr Kuleshov
Training normalizing flow generative models can be challenging due to the need to calculate computationally expensive determinants of Jacobians.
2 code implementations • 30 May 2022 • Subham Sekhar Sahoo, Anselm Paulus, Marin Vlastelica, Vít Musil, Volodymyr Kuleshov, Georg Martius
Embedding discrete solvers as differentiable layers has given modern deep learning architectures combinatorial expressivity and discrete reasoning capabilities.
Ranked #1 on Density Estimation on MNIST
2 code implementations • 24 May 2022 • Richa Rastogi, Yair Schiff, Alon Hacohen, Zhaozhi Li, Ian Lee, Yuntian Deng, Mert R. Sabuncu, Volodymyr Kuleshov
We introduce semi-parametric inducing point networks (SPIN), a general-purpose architecture that can query the training set at inference time in a compute-efficient manner.
no code implementations • 18 Mar 2022 • Shachi Deshpande, Kaiwen Wang, Dhruv Sreenivas, Zheng Li, Volodymyr Kuleshov
Oftentimes, the confounders are unobserved, but we have access to large amounts of additional unstructured data (images, text) that contain valuable proxy signal about the missing confounders.
no code implementations • 14 Dec 2021 • Volodymyr Kuleshov, Shachi Deshpande
Accurate probabilistic predictions can be characterized by two properties -- calibration and sharpness.
no code implementations • 12 Dec 2021 • Volodymyr Kuleshov, Evgenii Nikishin, Shantanu Thakoor, Tingfung Lau, Stefano Ermon
In this work, we seek to understand and extend adversarial examples across domains in which inputs are discrete, particularly across new domains, such as computational biology.
no code implementations • ICLR 2022 • Phillip Si, Allan Bishop, Volodymyr Kuleshov
Numerous applications of machine learning involve representing probability distributions over high-dimensional data.
no code implementations • 8 Dec 2021 • Shachi Deshpande, Charles Marx, Volodymyr Kuleshov
Accurate uncertainty estimates are important in sequential model-based decision-making tasks such as Bayesian optimization.
no code implementations • 31 Oct 2021 • BoJian Hou, Hao Zhang, Gur Ladizhinsky, Stephen Yang, Volodymyr Kuleshov, Fei Wang, Qian Yang
As a result, clinicians cannot easily or rapidly scrutinize the CDSS recommendation when facing a difficult diagnosis or treatment decision in practice.
no code implementations • 29 Sep 2021 • Volodymyr Kuleshov, Shachi Deshpande
Predictive uncertainties can be characterized by two properties---calibration and sharpness.
no code implementations • 1 Jan 2021 • Yong Huang, Edgar Mariano Marroquin, Volodymyr Kuleshov
Here, we introduce Multi-Modal Multitask MIMIC-III (M3) — a dataset and benchmark for evaluating machine learning algorithms in the healthcare domain.
1 code implementation • NeurIPS 2019 • Sawyer Birnbaum, Volodymyr Kuleshov, Zayd Enam, Pang Wei W. Koh, Stefano Ermon
Learning representations that accurately capture long-range dependencies in sequential inputs --- including text, audio, and genomic data --- is a key problem in deep learning.
Ranked #6 on Audio Super-Resolution on VCTK Multi-Speaker
1 code implementation • 14 Sep 2019 • Sawyer Birnbaum, Volodymyr Kuleshov, Zayd Enam, Pang Wei Koh, Stefano Ermon
Learning representations that accurately capture long-range dependencies in sequential inputs -- including text, audio, and genomic data -- is a key problem in deep learning.
Ranked #2 on Audio Super-Resolution on Voice Bank corpus (VCTK) (using extra training data)
1 code implementation • 19 Jun 2019 • Ali Malik, Volodymyr Kuleshov, Jiaming Song, Danny Nemer, Harlan Seymour, Stefano Ermon
Estimates of predictive uncertainty are important for accurate model-based planning and reinforcement learning.
Model-based Reinforcement Learning reinforcement-learning +1
1 code implementation • ICML 2018 • Volodymyr Kuleshov, Nathan Fenner, Stefano Ermon
Methods for reasoning under uncertainty are a key building block of accurate and reliable machine learning systems.
1 code implementation • 27 May 2018 • Hongyu Ren, Russell Stewart, Jiaming Song, Volodymyr Kuleshov, Stefano Ermon
Constraint-based learning reduces the burden of collecting labels by having users specify general properties of structured outputs, such as constraints imposed by physical laws.
no code implementations • ICLR 2018 • Volodymyr Kuleshov, Shantanu Thakoor, Tingfung Lau, Stefano Ermon
Modern machine learning algorithms are often susceptible to adversarial examples — maliciously crafted inputs that are undetectable by humans but that fool the algorithm into producing undesirable behavior.
no code implementations • NeurIPS 2017 • Volodymyr Kuleshov, Stefano Ermon
Many problems in machine learning are naturally expressed in the language of undirected graphical models.
4 code implementations • 2 Aug 2017 • Volodymyr Kuleshov, S. Zayd Enam, Stefano Ermon
We introduce a new audio processing technique that increases the sampling rate of signals such as speech or music using deep convolutional neural networks.
Ranked #3 on Audio Super-Resolution on Voice Bank corpus (VCTK) (using extra training data)
no code implementations • 13 Jul 2016 • Volodymyr Kuleshov, Stefano Ermon
Assessing uncertainty is an important step towards ensuring the safety and reliability of machine learning systems.
1 code implementation • NeurIPS 2015 • Volodymyr Kuleshov, Percy S. Liang
In user-facing applications, displaying calibrated confidence measures---probabilities that correspond to true frequency---can be as important as obtaining high accuracy.
1 code implementation • 29 Jan 2015 • Volodymyr Kuleshov, Arun Tejasvi Chaganty, Percy Liang
Tensor factorization arises in many machine learning applications, such knowledge base modeling and parameter estimation in latent variable models.
no code implementations • 25 Feb 2014 • Volodymyr Kuleshov, Doina Precup
Although the design of clinical trials has been one of the principal practical problems motivating research on multi-armed bandits, bandit algorithms have never been evaluated as potential treatment allocation strategies.