You need to log in to edit.

You can create a new account if you don't have one.

Or, discuss a change on Slack.

You can create a new account if you don't have one.

Or, discuss a change on Slack.

no code implementations • 6 Aug 2023 • Rongguang Wang, Guray Erus, Pratik Chaudhari, Christos Davatzikos

In some cases, it is even better than training on all data from the target group, because it leverages the diversity and size of a larger training set.

no code implementations • 12 Jul 2023 • Yao Liu, Pratik Chaudhari, Rasool Fakoor

The main challenge of offline reinforcement learning, where data is limited, arises from a sequence of counterfactual reasoning dilemmas within the realm of potential actions: What if we were to choose a different course of action?

no code implementations • 29 May 2023 • Stefano Soatto, Paulo Tabuada, Pratik Chaudhari, Tian Yu Liu

We then characterize the subset of meanings that can be reached by the state of the LLMs for some input prompt, and show that a well-trained bot can reach any meaning albeit with small probability.

no code implementations • 27 May 2023 • Daiwei Chen, Weikai Chang, Pratik Chaudhari

We exploit a formal correspondence between thermodynamics and inference, where the number of samples can be thought of as the inverse temperature, to define a "learning capacity'' which is a measure of the effective dimensionality of a model.

1 code implementation • 2 May 2023 • Jialin Mao, Itay Griniasty, Han Kheng Teoh, Rahul Ramesh, Rubing Yang, Mark K. Transtrum, James P. Sethna, Pratik Chaudhari

We develop information-geometric techniques to analyze the trajectories of the predictions of deep networks during training.

no code implementations • 22 Apr 2023 • Yansong Gao, Zhihong Pan, Xin Zhou, Le Kang, Pratik Chaudhari

This work analyzes how the backward error affects the diffusion ODEs and the sample quality in DDPMs.

no code implementations • 15 Mar 2023 • Rohit Jena, Pratik Chaudhari, James Gee, Ganesh Iyer, Siddharth Choudhary, Brandon M. Smith

Human reconstruction and synthesis from monocular RGB videos is a challenging problem due to clothing, occlusion, texture discontinuities and sharpness, and framespecific pose changes.

1 code implementation • 31 Oct 2022 • Rahul Ramesh, Jialin Mao, Itay Griniasty, Rubing Yang, Han Kheng Teoh, Mark Transtrum, James P. Sethna, Pratik Chaudhari

We develop information geometric techniques to understand the representations learned by deep networks when they are trained on different tasks using supervised, meta-, semi-supervised and contrastive learning.

no code implementations • 4 Oct 2022 • Rasool Fakoor, Jonas Mueller, Zachary C. Lipton, Pratik Chaudhari, Alexander J. Smola

Real-world deployment of machine learning models is challenging because data evolves over time.

1 code implementation • 23 Aug 2022 • Ashwin De Silva, Rahul Ramesh, Carey E. Priebe, Pratik Chaudhari, Joshua T. Vogelstein

In this work, we show a counter-intuitive phenomenon: the generalization error of a task can be a non-monotonic function of the number of OOD samples.

no code implementations • CVPR 2023 • Rohit Jena, Lukas Zhornyak, Nehal Doiphode, Pratik Chaudhari, Vivek Buch, James Gee, Jianbo Shi

Correctness of instance segmentation constitutes counting the number of objects, correctly localizing all predictions and classifying each localized prediction.

no code implementations • 11 Jun 2022 • Ramya Muthukrishnan, Angelina Heyler, Keshava Katti, Sarthak Pati, Walter Mankowski, Aprupa Alahari, Michael Sanborn, Emily F. Conant, Christopher Scott, Stacey Winham, Celine Vachon, Pratik Chaudhari, Despina Kontos, Spyridon Bakas

Assessing breast cancer risk from imaging remains a subjective process, in which radiologists employ simple computer aided detection (CAD) systems or qualitative visual assessment to estimate breast percent density (PD).

no code implementations • 26 May 2022 • Rongguang Wang, Pratik Chaudhari, Christos Davatzikos

Despite the great promise that machine learning has offered in many fields of medicine, it has also raised concerns about potential biases and poor generalization across genders, age distributions, races and ethnicities, hospitals, and data acquisition equipment and protocols.

no code implementations • 25 Feb 2022 • Shiyun Xu, Zhiqi Bu, Pratik Chaudhari, Ian J. Barnett

In order to empower NAM with feature selection and improve the generalization, we propose the sparse neural additive models (SNAM) that employ the group sparsity regularization (e. g. Group LASSO), where each feature is learned by a sub-network whose trainable parameters are clustered as a group.

2 code implementations • pproximateinference AABI Symposium 2022 • Yansong Gao, Rahul Ramesh, Pratik Chaudhari

Such priors enable the task to maximally affect the Bayesian posterior, e. g., reference priors depend upon the number of samples available for learning the task and for very small sample sizes, the prior puts more probability mass on low-complexity models in the hypothesis space.

no code implementations • 19 Jan 2022 • Ashwin De Silva, Rahul Ramesh, Lyle Ungar, Marshall Hussain Shuler, Noah J. Cowan, Michael Platt, Chen Li, Leyla Isik, Seung-Eon Roh, Adam Charles, Archana Venkataraman, Brian Caffo, Javier J. How, Justus M Kebschull, John W. Krakauer, Maxim Bichuch, Kaleab Alemayehu Kinfu, Eva Yezerets, Dinesh Jayaraman, Jong M. Shin, Soledad Villar, Ian Phillips, Carey E. Priebe, Thomas Hartung, Michael I. Miller, Jayanta Dey, Ningyuan, Huang, Eric Eaton, Ralph Etienne-Cummings, Elizabeth L. Ogburn, Randal Burns, Onyema Osuagwu, Brett Mensh, Alysson R. Muotri, Julia Brown, Chris White, Weiwei Yang, Andrei A. Rusu, Timothy Verstynen, Konrad P. Kording, Pratik Chaudhari, Joshua T. Vogelstein

We conjecture that certain sequences of tasks are not retrospectively learnable (in which the data distribution is fixed), but are prospectively learnable (in which distributions may be dynamic), suggesting that prospective learning is more difficult in kind than retrospective learning.

1 code implementation • 27 Oct 2021 • Rubing Yang, Jialin Mao, Pratik Chaudhari

This structure is mirrored in a network trained on this data: we show that the Hessian and the Fisher Information Matrix (FIM) have eigenvalues that are spread uniformly over exponentially large ranges.

no code implementations • ICLR 2022 • Rahul Ramesh, Pratik Chaudhari

This paper argues that continual learning methods can benefit by splitting the capacity of the learner across multiple models.

1 code implementation • 12 Jun 2021 • Rongguang Wang, Pratik Chaudhari, Christos Davatzikos

Heterogeneity in medical data, e. g., from data collected at different sites and with different protocols in a clinical study, is a fundamental hurdle for accurate prediction using machine learning models, as such models often fail to generalize well.

2 code implementations • 6 Jun 2021 • Rahul Ramesh, Pratik Chaudhari

We use statistical learning theory and experimental analysis to show how multiple tasks can interact with each other in a non-trivial fashion when a single model is trained on them.

Ranked #1 on Continual Learning on Cifar100 (20 tasks)

1 code implementation • 26 Mar 2021 • Wenbo Zhang, Karl Schmeckpeper, Pratik Chaudhari, Kostas Daniilidis

We empirically demonstrate that our approach can predict the rope state accurately up to ten steps into the future and that our algorithm can find the optimal action given an initial state and a goal state.

no code implementations • 23 Mar 2021 • Rongguang Wang, Pratik Chaudhari, Christos Davatzikos

We can also tackle situations where we do not have access to ground-truth labels on target data; we show how one can use auxiliary tasks for adaptation; these tasks employ covariates such as age, gender and race which are easy to obtain but nevertheless correlated to the main task.

1 code implementation • NeurIPS 2021 • Rasool Fakoor, Jonas Mueller, Kavosh Asadi, Pratik Chaudhari, Alexander J. Smola

Reliant on too many experiments to learn good actions, current Reinforcement Learning (RL) algorithms have limited applicability in real-world settings, which can be too expensive to allow exploration.

1 code implementation • 16 Nov 2020 • Christopher D. Hsu, Heejin Jeong, George J. Pappas, Pratik Chaudhari

Our method can handle an arbitrary number of pursuers and targets; we show results for tasks consisting up to 1000 pursuers tracking 1000 targets.

Multi-agent Reinforcement Learning
reinforcement-learning
**+1**

1 code implementation • NeurIPS Workshop DL-IG 2020 • Yansong Gao, Pratik Chaudhari

Using tools in information geometry, the distance is defined to be the length of the shortest weight trajectory on a Riemannian manifold as a classifier is fitted on an interpolated task.

1 code implementation • 17 Aug 2020 • Xiaoyi Chen, Pratik Chaudhari

Autonomous navigation in crowded, complex urban environments requires interacting with other agents on the road.

no code implementations • 3 Aug 2020 • Marco Maggipinto, Gian Antonio Susto, Pratik Chaudhari

This paper introduces two simple techniques to improve off-policy Reinforcement Learning (RL) algorithms.

no code implementations • 26 Jun 2020 • Rasool Fakoor, Pratik Chaudhari, Alexander J. Smola

This paper prescribes a suite of techniques for off-policy Reinforcement Learning (RL) that simplify the training process and reduce the sample complexity.

1 code implementation • NeurIPS 2020 • Rasool Fakoor, Jonas Mueller, Nick Erickson, Pratik Chaudhari, Alexander J. Smola

Automated machine learning (AutoML) can produce complex model ensembles by stacking, bagging, and boosting many individual models like trees, deep networks, and nearest neighbor estimators.

1 code implementation • 10 May 2020 • Achin Jain, Matthew O'Kelly, Pratik Chaudhari, Manfred Morari

Autonomous race cars require perception, estimation, planning, and control modules which work together asynchronously while driving at the limit of a vehicle's handling capability.

no code implementations • 6 Apr 2020 • Rasool Fakoor, Pratik Chaudhari, Jonas Mueller, Alexander J. Smola

We present TraDE, a self-attention-based architecture for auto-regressive density estimation with continuous and discrete valued data.

no code implementations • ICML 2020 • Yansong Gao, Pratik Chaudhari

This paper employs a formal connection of machine learning with thermodynamics to characterize the quality of learnt representations for transfer learning.

1 code implementation • ICLR 2020 • Hao Li, Pratik Chaudhari, Hao Yang, Michael Lam, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto

Our findings challenge common practices of fine-tuning and encourages deep learning practitioners to rethink the hyperparameters for fine-tuning.

no code implementations • 8 Oct 2019 • Matteo Terzi, Gian Antonio Susto, Pratik Chaudhari

Adversarial Training is a training procedure aiming at providing models that are robust to worst-case perturbations around predefined points.

1 code implementation • ICLR 2020 • Rasool Fakoor, Pratik Chaudhari, Stefano Soatto, Alexander J. Smola

This paper introduces Meta-Q-Learning (MQL), a new off-policy algorithm for meta-Reinforcement Learning (meta-RL).

3 code implementations • ICLR 2020 • Guneet S. Dhillon, Pratik Chaudhari, Avinash Ravichandran, Stefano Soatto

When fine-tuned transductively, this outperforms the current state-of-the-art on standard datasets such as Mini-ImageNet, Tiered-ImageNet, CIFAR-FS and FC-100 with the same hyper-parameters.

1 code implementation • 5 May 2019 • Rasool Fakoor, Pratik Chaudhari, Alexander J. Smola

Extensive experiments on the Atari-2600 and MuJoCo benchmark suites show that this simple technique is effective in reducing the sample complexity of state-of-the-art algorithms.

no code implementations • ICLR 2018 • Pratik Chaudhari, Stefano Soatto

So SGD does perform variational inference, but for a different loss than the one used to compute the gradients.

no code implementations • 3 Jul 2017 • Pratik Chaudhari, Carlo Baldassi, Riccardo Zecchina, Stefano Soatto, Ameet Talwalkar, Adam Oberman

We propose a new algorithm called Parle for parallel training of deep networks that converges 2-4x faster than a data-parallel implementation of SGD, while achieving significantly improved error rates that are nearly state-of-the-art on several benchmarks including CIFAR-10 and CIFAR-100, without introducing any additional hyper-parameters.

no code implementations • 17 Apr 2017 • Pratik Chaudhari, Adam Oberman, Stanley Osher, Stefano Soatto, Guillaume Carlier

In this paper we establish a connection between non-convex optimization methods for training deep neural networks and nonlinear partial differential equations (PDEs).

2 code implementations • 6 Nov 2016 • Pratik Chaudhari, Anna Choromanska, Stefano Soatto, Yann Lecun, Carlo Baldassi, Christian Borgs, Jennifer Chayes, Levent Sagun, Riccardo Zecchina

This paper proposes a new optimization algorithm called Entropy-SGD for training deep neural networks that is motivated by the local geometry of the energy landscape.

no code implementations • 20 Nov 2015 • Pratik Chaudhari, Stefano Soatto

Specifically, we show that a regularization term akin to a magnetic field can be modulated with a single scalar parameter to transition the loss function from a complex, non-convex landscape with exponentially many local minima, to a phase with a polynomial number of minima, all the way down to a trivial landscape with a unique minimum.

Cannot find the paper you are looking for? You can
Submit a new open access paper.

Contact us on:
hello@paperswithcode.com
.
Papers With Code is a free resource with all data licensed under CC-BY-SA.