Search Results for author: Aditya Grover

Found 62 papers, 44 papers with code

Mamba-ND: Selective State Space Modeling for Multi-Dimensional Data

1 code implementation8 Feb 2024 Shufan Li, Harkanwar Singh, Aditya Grover

A recent architecture, Mamba, based on state space models has been shown to achieve comparable performance for modeling text sequences, while scaling linearly with the sequence length.

Action Recognition Weather Forecasting

InstructAny2Pix: Flexible Visual Editing via Multimodal Instruction Following

1 code implementation11 Dec 2023 Shufan Li, Harkanwar Singh, Aditya Grover

We demonstrate that our system can perform a series of novel instruction-guided editing tasks.

Instruction Following

Guided Flows for Generative Modeling and Decision Making

no code implementations22 Nov 2023 Qinqing Zheng, Matt Le, Neta Shaul, Yaron Lipman, Aditya Grover, Ricky T. Q. Chen

Classifier-free guidance is a key component for enhancing the performance of conditional generative models across diverse tasks.

Conditional Image Generation Decision Making +3

VideoCon: Robust Video-Language Alignment via Contrast Captions

1 code implementation15 Nov 2023 Hritik Bansal, Yonatan Bitton, Idan Szpektor, Kai-Wei Chang, Aditya Grover

Despite being (pre)trained on a massive amount of data, state-of-the-art video-language alignment models are not robust to semantically-plausible contrastive changes in the video captions.

Language Modelling Large Language Model +5

ExPT: Synthetic Pretraining for Few-Shot Experimental Design

1 code implementation NeurIPS 2023 Tung Nguyen, Sudhanshu Agrawal, Aditya Grover

In this work, we address the more challenging yet realistic setting of few-shot experimental design, where only a few labeled data points of input designs and their corresponding values are available.

Experimental Design In-Context Learning

Group Preference Optimization: Few-Shot Alignment of Large Language Models

no code implementations17 Oct 2023 Siyan Zhao, John Dang, Aditya Grover

We introduce Group Preference Optimization (GPO), an alignment framework that steers language models to preferences of individual groups in a few-shot manner.

Few-Shot Learning

High Dimensional Causal Inference with Variational Backdoor Adjustment

1 code implementation9 Oct 2023 Daniel Israel, Aditya Grover, Guy Van Den Broeck

For example, in medical settings, backdoor adjustment can be used to control for confounding and estimate the effectiveness of a treatment.

Causal Inference Variational Inference

Peering Through Preferences: Unraveling Feedback Acquisition for Aligning Large Language Models

1 code implementation30 Aug 2023 Hritik Bansal, John Dang, Aditya Grover

In particular, we find that LLMs that leverage rankings data for alignment (say model X) are preferred over those that leverage ratings data (say model Y), with a rank-based evaluation protocol (is X/Y's response better than reference response?)

ClimateLearn: Benchmarking Machine Learning for Weather and Climate Modeling

1 code implementation NeurIPS 2023 Tung Nguyen, Jason Jewik, Hritik Bansal, Prakhar Sharma, Aditya Grover

Modeling weather and climate is an essential endeavor to understand the near- and long-term impacts of climate change, as well as inform technology and policymaking for adaptation and mitigation efforts.

Benchmarking Weather Forecasting

Diffusion Models for Black-Box Optimization

1 code implementation12 Jun 2023 Siddarth Krishnamoorthy, Satvik Mehul Mashkaria, Aditya Grover

The goal of offline black-box optimization (BBO) is to optimize an expensive black-box function using a fixed dataset of function evaluations.

Denoising

Scaling Pareto-Efficient Decision Making Via Offline Multi-Objective RL

1 code implementation30 Apr 2023 Baiting Zhu, Meihua Dang, Aditya Grover

In this work, we propose a new data-driven setup for offline MORL, where we wish to learn a preference-agnostic policy agent using only a finite dataset of offline demonstrations of other agents and their preferences.

Decision Making Multi-Objective Reinforcement Learning

CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning

1 code implementation ICCV 2023 Hritik Bansal, Nishad Singhi, Yu Yang, Fan Yin, Aditya Grover, Kai-Wei Chang

Multimodal contrastive pretraining has been used to train multimodal representation models, such as CLIP, on large amounts of paired image-text data.

Backdoor Attack Contrastive Learning +1

Leaving Reality to Imagination: Robust Classification via Generated Datasets

1 code implementation5 Feb 2023 Hritik Bansal, Aditya Grover

Recent research on robustness has revealed significant performance gaps between neural image classifiers trained on datasets that are similar to the test set, and those that are from a naturally shifted distribution, such as sketches, paintings, and animations of the object categories observed during training.

Classification Robust classification

ClimaX: A foundation model for weather and climate

1 code implementation24 Jan 2023 Tung Nguyen, Johannes Brandstetter, Ashish Kapoor, Jayesh K. Gupta, Aditya Grover

We develop and demonstrate ClimaX, a flexible and generalizable deep learning model for weather and climate science that can be trained using heterogeneous datasets spanning different variables, spatio-temporal coverage, and physical groundings.

Self-Supervised Learning Weather Forecasting

Masked Autoencoding for Scalable and Generalizable Decision Making

1 code implementation23 Nov 2022 Fangchen Liu, Hao liu, Aditya Grover, Pieter Abbeel

We are interested in learning scalable agents for reinforcement learning that can learn from large-scale, diverse sequential data similar to current large vision and language models.

Decision Making Offline RL +2

Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectories

1 code implementation12 Oct 2022 Qinqing Zheng, Mikael Henaff, Brandon Amos, Aditya Grover

For this setting, we develop and study a simple meta-algorithmic pipeline that learns an inverse dynamics model on the labelled data to obtain proxy-labels for the unlabelled data, followed by the use of any offline RL algorithm on the true and proxy-labelled trajectories.

D4RL Offline RL +2

Reliable Conditioning of Behavioral Cloning for Offline Reinforcement Learning

1 code implementation11 Oct 2022 Tung Nguyen, Qinqing Zheng, Aditya Grover

We study CWBC in the context of RvS (Emmons et al., 2021) and Decision Transformers (Chen et al., 2021), and show that CWBC significantly boosts their performance on various benchmarks.

Offline RL reinforcement-learning +1

Matching Normalizing Flows and Probability Paths on Manifolds

no code implementations11 Jul 2022 Heli Ben-Hamu, samuel cohen, Joey Bose, Brandon Amos, Aditya Grover, Maximilian Nickel, Ricky T. Q. Chen, Yaron Lipman

Continuous Normalizing Flows (CNFs) are a class of generative models that transform a prior distribution to a model distribution by solving an ordinary differential equation (ODE).

Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modeling

1 code implementation9 Jul 2022 Tung Nguyen, Aditya Grover

We propose Transformer Neural Processes (TNPs), a new member of the NP family that casts uncertainty-aware meta learning as a sequence modeling problem.

Bayesian Optimization Decision Making +3

Short-range forecasts of global precipitation using deep learning-augmented numerical weather prediction

no code implementations23 Jun 2022 Manmeet Singh, Vaisakh S B, Nachiketa Acharya, Aditya Grover, Suryachandra A Rao, Bipin Kumar, Zong-Liang Yang, Dev Niyogi

We augment the output of the well-known NWP model CFSv2 with deep learning to create a hybrid model that improves short-range global precipitation at 1-, 2-, and 3-day lead times.

Generative Pretraining for Black-Box Optimization

1 code implementation22 Jun 2022 Siddarth Krishnamoorthy, Satvik Mehul Mashkaria, Aditya Grover

Many problems in science and engineering involve optimizing an expensive black-box function over a high-dimensional space.

CyCLIP: Cyclic Contrastive Language-Image Pretraining

1 code implementation28 May 2022 Shashank Goel, Hritik Bansal, Sumit Bhatia, Ryan A. Rossi, Vishwa Vinay, Aditya Grover

Recent advances in contrastive representation learning over paired image-text data have led to models such as CLIP that achieve state-of-the-art performance for zero-shot classification and distributional robustness.

Representation Learning Visual Reasoning +1

Imitating, Fast and Slow: Robust learning from demonstrations via decision-time planning

no code implementations7 Apr 2022 Carl Qi, Pieter Abbeel, Aditya Grover

The goal of imitation learning is to mimic expert behavior from demonstrations, without access to an explicit reward signal.

Imitation Learning reinforcement-learning +2

It Takes Four to Tango: Multiagent Selfplay for Automatic Curriculum Generation

no code implementations22 Feb 2022 Yuqing Du, Pieter Abbeel, Aditya Grover

Training such agents efficiently requires automatic generation of a goal curriculum.

Online Decision Transformer

2 code implementations11 Feb 2022 Qinqing Zheng, Amy Zhang, Aditya Grover

Recent work has shown that offline reinforcement learning (RL) can be formulated as a sequence modeling problem (Chen et al., 2021; Janner et al., 2021) and solved via approaches similar to large-scale language modeling.

D4RL Efficient Exploration +2

BARACK: Partially Supervised Group Robustness With Guarantees

no code implementations31 Dec 2021 Nimit S. Sohoni, Maziar Sanjabi, Nicolas Ballas, Aditya Grover, Shaoliang Nie, Hamed Firooz, Christopher Ré

Theoretically, we provide generalization bounds for our approach in terms of the worst-group performance, which scale with respect to both the total number of training points and the number of training points with group labels.

Fairness Generalization Bounds

BCD Nets: Scalable Variational Approaches for Bayesian Causal Discovery

1 code implementation NeurIPS 2021 Chris Cundy, Aditya Grover, Stefano Ermon

We propose Bayesian Causal Discovery Nets (BCD Nets), a variational inference framework for estimating a distribution over DAGs characterizing a linear-Gaussian SEM.

Causal Discovery Stochastic Optimization +1

It Takes Four to Tango: Multiagent Self Play for Automatic Curriculum Generation

1 code implementation ICLR 2022 Yuqing Du, Pieter Abbeel, Aditya Grover

We are interested in training general-purpose reinforcement learning agents that can solve a wide variety of goals.

CAGE: Probing Causal Relationships in Deep Generative Models

no code implementations29 Sep 2021 Joey Bose, Ricardo Pio Monti, Aditya Grover

Deep generative models excel at generating complex, high-dimensional data, often exhibiting impressive generalization beyond the training distribution.

Robust classification Synthetic Data Generation

Moser Flow: Divergence-based Generative Modeling on Manifolds

1 code implementation NeurIPS 2021 Noam Rozen, Aditya Grover, Maximilian Nickel, Yaron Lipman

MF also produces a CNF via a solution to the change-of-variable formula, however differently from other CNF methods, its model (learned) density is parameterized as the source (prior) density minus the divergence of a neural network (NN).

Density Estimation

Learning from an Exploring Demonstrator: Optimal Reward Estimation for Bandits

1 code implementation28 Jun 2021 Wenshuo Guo, Kumar Krishna Agrawal, Aditya Grover, Vidya Muthukumar, Ashwin Pananjady

We introduce the "inverse bandit" problem of estimating the rewards of a multi-armed bandit instance from observing the learning process of a low-regret demonstrator.

Experimental Design

JUMBO: Scalable Multi-task Bayesian Optimization using Offline Data

1 code implementation2 Jun 2021 Kourosh Hakhamaneshi, Pieter Abbeel, Vladimir Stojanovic, Aditya Grover

Such a decomposition can dynamically control the reliability of information derived from the online and offline data and the use of pretrained neural networks permits scalability to large offline datasets.

Bayesian Optimization Gaussian Processes

Pretrained Transformers as Universal Computation Engines

4 code implementations9 Mar 2021 Kevin Lu, Aditya Grover, Pieter Abbeel, Igor Mordatch

We investigate the capability of a transformer pretrained on natural language to generalize to other modalities with minimal finetuning -- in particular, without finetuning of the self-attention and feedforward layers of the residual blocks.

Anytime Sampling for Autoregressive Models via Ordered Autoencoding

1 code implementation ICLR 2021 Yilun Xu, Yang song, Sahaj Garg, Linyuan Gong, Rui Shu, Aditya Grover, Stefano Ermon

Experimentally, we demonstrate in several image and audio generation tasks that sample quality degrades gracefully as we reduce the computational budget for sampling.

Audio Generation Computational Efficiency

Robust Imitation via Decision-Time Planning

no code implementations1 Jan 2021 Carl Qi, Pieter Abbeel, Aditya Grover

The goal of imitation learning is to mimic expert behavior from demonstrations, without access to an explicit reward signal.

Imitation Learning reinforcement-learning +2

PiRank: Scalable Learning To Rank via Differentiable Sorting

1 code implementation NeurIPS 2021 Robin Swezey, Aditya Grover, Bruno Charron, Stefano Ermon

A key challenge with machine learning approaches for ranking is the gap between the performance metrics of interest and the surrogate loss functions that can be optimized with gradient-based methods.

Learning-To-Rank

Reset-Free Lifelong Learning with Skill-Space Planning

1 code implementation ICLR 2021 Kevin Lu, Aditya Grover, Pieter Abbeel, Igor Mordatch

We propose Lifelong Skill Planning (LiSP), an algorithmic framework for non-episodic lifelong RL based on planning in an abstract space of higher-order skills.

Reinforcement Learning (RL)

Permutation Invariant Graph Generation via Score-Based Generative Modeling

1 code implementation2 Mar 2020 Chenhao Niu, Yang song, Jiaming Song, Shengjia Zhao, Aditya Grover, Stefano Ermon

In particular, we design a permutation equivariant, multi-channel graph neural network to model the gradient of the data distribution at the input graph (a. k. a., the score function).

Graph Generation

Fair Generative Modeling via Weak Supervision

1 code implementation ICML 2020 Kristy Choi, Aditya Grover, Trisha Singh, Rui Shu, Stefano Ermon

Real-world datasets are often biased with respect to key demographic factors such as race and gender.

Image Generation

Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting

2 code implementations NeurIPS 2019 Aditya Grover, Jiaming Song, Alekh Agarwal, Kenneth Tran, Ashish Kapoor, Eric Horvitz, Stefano Ermon

A standard technique to correct this bias is importance sampling, where samples from the model are weighted by the likelihood ratio under model and true distributions.

Data Augmentation

Bias Correction of Learned Generative Models via Likelihood-free Importance Weighting

no code implementations ICLR Workshop DeepGenStruct 2019 Aditya Grover, Jiaming Song, Ashish Kapoor, Kenneth Tran, Alekh Agarwal, Eric Horvitz, Stefano Ermon

A standard technique to correct this bias is by importance weighting samples from the model by the likelihood ratio under the model and true distributions.

Data Augmentation

Uncertainty Autoencoders: Learning Compressed Representations via Variational Information Maximization

no code implementations26 Dec 2018 Aditya Grover, Stefano Ermon

We treat the low-dimensional projections as noisy latent representations of an autoencoder and directly learn both the acquisition (i. e., encoding) and amortized recovery (i. e., decoding) procedures.

Dimensionality Reduction Representation Learning

Learning Controllable Fair Representations

3 code implementations11 Dec 2018 Jiaming Song, Pratyusha Kalluri, Aditya Grover, Shengjia Zhao, Stefano Ermon

Learning data representations that are transferable and are fair with respect to certain protected attributes is crucial to reducing unfair decisions while preserving the utility of the data.

Fairness

Streamlining Variational Inference for Constraint Satisfaction Problems

1 code implementation NeurIPS 2018 Aditya Grover, Tudor Achim, Stefano Ermon

Several algorithms for solving constraint satisfaction problems are based on survey propagation, a variational inference scheme used to obtain approximate marginal probability estimates for variable assignments.

Variational Inference

Neural Joint Source-Channel Coding

1 code implementation19 Nov 2018 Kristy Choi, Kedar Tatwawadi, Aditya Grover, Tsachy Weissman, Stefano Ermon

For reliable transmission across a noisy communication channel, classical results from information theory show that it is asymptotically optimal to separate out the source and channel coding processes.

Modeling Sparse Deviations for Compressed Sensing using Generative Models

2 code implementations ICML 2018 Manik Dhar, Aditya Grover, Stefano Ermon

In compressed sensing, a small number of linear measurements can be used to reconstruct an unknown signal.

Variational Rejection Sampling

no code implementations5 Apr 2018 Aditya Grover, Ramki Gummadi, Miguel Lazaro-Gredilla, Dale Schuurmans, Stefano Ermon

Learning latent variable models with stochastic variational inference is challenging when the approximate posterior is far from the true posterior, due to high variance in the gradient estimates.

Variational Inference

Best arm identification in multi-armed bandits with delayed feedback

no code implementations29 Mar 2018 Aditya Grover, Todor Markov, Peter Attia, Norman Jin, Nicholas Perkins, Bryan Cheong, Michael Chen, Zi Yang, Stephen Harris, William Chueh, Stefano Ermon

We propose a generalization of the best arm identification problem in stochastic multi-armed bandits (MAB) to the setting where every pull of an arm is associated with delayed feedback.

Hyperparameter Optimization Multi-Armed Bandits

Flow-GAN: Combining Maximum Likelihood and Adversarial Learning in Generative Models

3 code implementations24 May 2017 Aditya Grover, Manik Dhar, Stefano Ermon

Implicit models such as generative adversarial networks (GAN) often generate better samples compared to explicit models trained by maximum likelihood.

Generative Adversarial Network

Boosted Generative Models

1 code implementation27 Feb 2017 Aditya Grover, Stefano Ermon

We propose a novel approach for using unsupervised boosting to create an ensemble of generative models, where models are trained in sequence to correct earlier mistakes.

Density Estimation General Classification

Variational Bayes on Monte Carlo Steroids

no code implementations NeurIPS 2016 Aditya Grover, Stefano Ermon

We provide a new approach for learning latent variable models based on optimizing our new bounds on the log-likelihood.

node2vec: Scalable Feature Learning for Networks

18 code implementations3 Jul 2016 Aditya Grover, Jure Leskovec

Taken together, our work represents a new way for efficiently learning state-of-the-art task-independent representations in complex networks.

Link Prediction Multi-Label Classification +2

Contextual Symmetries in Probabilistic Graphical Models

no code implementations30 Jun 2016 Ankit Anand, Aditya Grover, Mausam, Parag Singla

We extend previous work on exploiting symmetries in the MCMC framework to the case of contextual symmetries.

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