publications

recent preprints

1. arXiv

   ClimaX: A foundation model for weather and climate

   Tung Nguyen, Johannes Brandstetter, Ashish Kapoor, Jayesh K Gupta, and Aditya Grover

   arXiv preprint arXiv:2301.10343, 2023

   Abs PDF
   Spotlight Oral Presentation at the ICLR Workshop on Tackling Climate Change with Machine Learning

   Most state-of-the-art approaches for weather and climate modeling are based on physics-informed numerical models of the atmosphere. These approaches aim to model the non-linear dynamics and complex interactions between multiple variables, which are challenging to approximate. Additionally, many such numerical models are computationally intensive, especially when modeling the atmospheric phenomenon at a fine-grained spatial and temporal resolution. Recent data-driven approaches based on machine learning instead aim to directly solve a downstream forecasting or projection task by learning a data-driven functional mapping using deep neural networks. However, these networks are trained using curated and homogeneous climate datasets for specific spatiotemporal tasks, and thus lack the generality of numerical models. 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. ClimaX extends the Transformer architecture with novel encoding and aggregation blocks that allow effective use of available compute while maintaining general utility. ClimaX is pre-trained with a self-supervised learning objective on climate datasets derived from CMIP6. The pre-trained ClimaX can then be fine-tuned to address a breadth of climate and weather tasks, including those that involve atmospheric variables and spatio-temporal scales unseen during pretraining. Compared to existing data-driven baselines, we show that this generality in ClimaX results in superior performance on benchmarks for weather forecasting and climate projections, even when pretrained at lower resolutions and compute budgets.

2. arXiv

   Leaving Reality to Imagination: Robust Classification via Generated Datasets

   Hritik Bansal, and Aditya Grover

   2023

   Abs PDF

   https://arxiv.org/abs/2302.02503

1. arXiv

   Generative pretraining for black-box optimization

   Siddarth Krishnamoorthy, Satvik Mehul Mashkaria, and Aditya Grover

   arXiv preprint arXiv:2206.10786, 2022

   Abs PDF
   Oral Presentation at the NeurIPS Workshop on Foundation Models for Decision Making

   Many problems in science and engineering involve optimizing an expensive black-box function over a high-dimensional space. For such black-box optimization (BBO) problems, we typically assume a small budget for online function evaluations, but also often have access to a fixed, offline dataset for pretraining. Prior approaches seek to utilize the offline data to approximate the function or its inverse but are not sufficiently accurate far from the data distribution. We propose BONET, a generative framework for pretraining a novel black-box optimizer using offline datasets. In BONET, we train an autoregressive model on fixed-length trajectories derived from an offline dataset. We design a sampling strategy to synthesize trajectories from offline data using a simple heuristic of rolling out monotonic transitions from low-fidelity to high-fidelity samples. Empirically, we instantiate BONET using a causally masked Transformer and evaluate it on Design-Bench, where we rank the best on average, outperforming state-of-the-art baselines.

2. arXiv

   Reliable Conditioning of Behavioral Cloning for Offline Reinforcement Learning

   Tung Nguyen, Qinqing Zheng, and Aditya Grover

   arXiv preprint arXiv:2210.05158, 2022

   Abs PDF

   Behavioral cloning (BC) provides a straightforward solution to offline RL by mimicking offline trajectories via supervised learning. Recent advances (Chen et al., 2021; Janner et al., 2021; Emmons et al., 2021) have shown that by conditioning on desired future returns, BC can perform competitively to their value-based counterparts, while enjoying much more simplicity and training stability. While promising, we show that these methods can be unreliable, as their performance may degrade significantly when conditioned on high, out-of-distribution (ood) returns. This is crucial in practice, as we often expect the policy to perform better than the offline dataset by conditioning on an ood value. We show that this unreliability arises from both the suboptimality of training data and model architectures. We propose ConserWeightive Behavioral Cloning (CWBC), a simple and effective method for improving the reliability of conditional BC with two key components: trajectory weighting and conservative regularization. Trajectory weighting upweights the high-return trajectories to reduce the train-test gap for BC methods, while conservative regularizer encourages the policy to stay close to the data distribution for ood conditioning. 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.

3. arXiv

   Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectories

   Qinqing Zheng, Mikael Henaff, Brandon Amos, and Aditya Grover

   arXiv preprint arXiv:2210.06518, 2022

   Abs PDF

   Natural agents can effectively learn from multiple data sources that differ in size, quality, and types of measurements. We study this heterogeneity in the context of offline reinforcement learning (RL) by introducing a new, practically motivated semi-supervised setting. Here, an agent has access to two sets of trajectories: labelled trajectories containing state, action, reward triplets at every timestep, along with unlabelled trajectories that contain only state and reward information. 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. Empirically, we find this simple pipeline to be highly successful - on several D4RL benchmarks, certain offline RL algorithms can match the performance of variants trained on a fully labelled dataset even when we label only 10% trajectories from the low return regime. To strengthen our understanding, we perform a large-scale controlled empirical study investigating the interplay of data-centric properties of the labelled and unlabelled datasets, with algorithmic design choices (e.g., choice of inverse dynamics, offline RL algorithm) to identify general trends and best practices for training RL agents on semi-supervised offline datasets.

journal and conference articles

2023

1. ICLR

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

   Baiting Zhu, Meihua Dang, and Aditya Grover

   In International Conference on Learning Representations (ICLR), 2023

   Abs PDF

   The goal of multi-objective reinforcement learning (MORL) is to learn policies that simultaneously optimize multiple competing objectives. In practice, an agent’s preferences over the objectives may not be known apriori, and hence, we require policies that can generalize to arbitrary preferences at test time. 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. The key contributions of this work are two-fold. First, we introduce D4MORL, (D)atasets for MORL that are specifically designed for offline settings. It contains 1.8 million annotated demonstrations obtained by rolling out reference policies that optimize for randomly sampled preferences on 6 MuJoCo environments with 2-3 objectives each. Second, we propose Pareto-Efficient Decision Agents (PEDA), a family of offline MORL algorithms that builds and extends Decision Transformers via a novel preference-and-return-conditioned policy. Empirically, we show that PEDA closely approximates the behavioral policy on the D4MORL benchmark and provides an excellent approximation of the Pareto-front with appropriate conditioning, as measured by the hypervolume and sparsity metrics.

2022

1. TMLR

   Controllable Generative Modeling via Causal Reasoning

   Joey Bose, Ricardo Pio Monti, and Aditya Grover

   Transactions of Machine Learning Research, 2022

   Abs PDF

   Deep latent variable generative models excel at generating complex, high-dimensional data, often exhibiting impressive generalization beyond the training distribution. However, many such models in use today are black-boxes trained on large unlabelled datasets with statistical objectives and lack an interpretable understanding of the latent space required for controlling the generative process. We propose CAGE, a framework for controllable generation in latent variable models based on causal reasoning. Given a pair of attributes, CAGE infers the implicit cause-effect relationships between these attributes as induced by a deep generative model. This is achieved by defining and estimating a novel notion of unit-level causal effects in the latent space of the generative model. Thereafter, we use the inferred cause-effect relationships to design a novel strategy for controllable generation based on counterfactual sampling. Through a series of large-scale synthetic and human evaluations, we demonstrate that generating counterfactual samples which respect the underlying causal relationships inferred via CAGE leads to subjectively more realistic images.

2. NeurIPS

   Masked Autoencoding for Scalable and Generalizable Decision Making

   Fangchen Liu, Hao Liu, Aditya Grover, and Pieter Abbeel

   In Advances in Neural Information Processing Systems (NeurIPS), 2022

   Abs PDF Code

   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. To this end, this paper presents masked decision prediction (MaskDP), a simple and scalable self-supervised pretraining method for reinforcement learning (RL) and behavioral cloning (BC). In our MaskDP approach, we employ a masked autoencoder (MAE) to state-action trajectories, wherein we randomly mask state and action tokens and reconstruct the missing data. By doing so, the model is required to infer masked out states and actions and extract information about dynamics. We find that masking different proportions of the input sequence significantly helps with learning a better model that generalizes well to multiple downstream tasks. In our empirical study we find that a MaskDP model gains the capability of zero-shot transfer to new BC tasks, such as single and multiple goal reaching, and it can zero-shot infer skills from a few example transitions. In addition, MaskDP transfers well to offline RL and shows promising scaling behavior w.r.t. to model size. It is amenable to data efficient finetuning, achieving competitive results with prior methods based on autoregressive pretraining.

3. NeurIPS

   CyCLIP: Cyclic Contrastive Language-Image Pretraining

   Shashank Goel, Hritik Bansal, Sumit Bhatia, Ryan A Rossi, Vishwa Vinay, and Aditya Grover

   In Advances in Neural Information Processing Systems (NeurIPS), 2022

   Abs PDF Code
   Oral Presentation [top 2%]

   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. Such models typically require joint reasoning in the image and text representation spaces for downstream inference tasks. Contrary to prior beliefs, we demonstrate that the image and text representations learned via a standard contrastive objective are not interchangeable and can lead to inconsistent downstream predictions. To mitigate this issue, we formalize consistency and propose CyCLIP, a framework for contrastive representation learning that explicitly optimizes for the learned representations to be geometrically consistent in the image and text space. In particular, we show that consistent representations can be learned by explicitly symmetrizing (a) the similarity between the two mismatched image-text pairs (cross-modal consistency); and (b) the similarity between the image-image pair and the text-text pair (in-modal consistency). Empirically, we show that the improved consistency in CyCLIP translates to significant gains over CLIP, with gains ranging from 10%-24% for zero-shot classification accuracy on standard benchmarks (CIFAR-10, CIFAR-100, ImageNet1K) and 10%-27% for robustness to various natural distribution shifts.

4. ICML

   Transformer neural processes: Uncertainty-aware meta learning via sequence modeling

   Tung Nguyen, and Aditya Grover

   In International Conference on Machine Learning (ICML), 2022

   Abs PDF Code

   Neural Processes (NPs) are a popular class of approaches for meta-learning. Similar to Gaussian Processes (GPs), NPs define distributions over functions and can estimate uncertainty in their predictions. However, unlike GPs, NPs and their variants suffer from underfitting and often have intractable likelihoods, which limit their applications in sequential decision making. We propose Transformer Neural Processes (TNPs), a new member of the NP family that casts uncertainty-aware meta learning as a sequence modeling problem. We learn TNPs via an autoregressive likelihood-based objective and instantiate it with a novel transformer-based architecture. The model architecture respects the inductive biases inherent to the problem structure, such as invariance to the observed data points and equivariance to the unobserved points. We further investigate knobs within the TNP framework that tradeoff expressivity of the decoding distribution with extra computation. Empirically, we show that TNPs achieve state-of-the-art performance on various benchmark problems, outperforming all previous NP variants on meta regression, image completion, contextual multi-armed bandits, and Bayesian optimization.

5. ICML

   Online decision transformer

   Qinqing Zheng, Amy Zhang, and Aditya Grover

   In International Conference on Machine Learning (ICML), 2022

   Abs PDF
   Long Oral Presentation

   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. However, any practical instantiation of RL also involves an online component, where policies pretrained on passive offline datasets are finetuned via task-specific interactions with the environment. We propose Online Decision Transformers (ODT), an RL algorithm based on sequence modeling that blends offline pretraining with online finetuning in a unified framework. Our framework uses sequence-level entropy regularizers in conjunction with autoregressive modeling objectives for sample-efficient exploration and finetuning. Empirically, we show that ODT is competitive with the state-of-the-art in abstractolute performance on the D4RL benchmark but shows much more significant gains during the finetuning procedure.

6. ICML

   Matching normalizing flows and probability paths on manifolds

   Heli Ben-Hamu, Samuel Cohen, Joey Bose, Brandon Amos, Aditya Grover, Maximilian Nickel, Ricky Chen, and Yaron Lipman

   In International Conference on Machine Learning (ICML), 2022

   Abs PDF

   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). We propose to train CNFs on manifolds by minimizing probability path divergence (PPD), a novel family of divergences between the probability density path generated by the CNF and a target probability density path. PPD is formulated using a logarithmic mass conservation formula which is a linear first order partial differential equation relating the log target probabilities and the CNF’s defining vector field. PPD has several key benefits over existing methods: it sidesteps the need to solve an ODE per iteration, readily applies to manifold data, scales to high dimensions, and is compatible with a large family of target paths interpolating pure noise and data in finite time. Theoretically, PPD is shown to bound classical probability divergences. Empirically, we show that CNFs learned by minimizing PPD achieve state-of-the-art results in likelihoods and sample quality on existing low-dimensional manifold benchmarks, and is the first example of a generative model to scale to moderately high dimensional manifolds.

7. ICLR

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

   Yuqing Du, Pieter Abbeel, and Aditya Grover

   In International Conference on Learning Representations (ICLR), 2022

   Abs PDF Code

   We are interested in training general-purpose reinforcement learning agents that can solve a wide variety of goals. Training such agents efficiently requires automatic generation of a goal curriculum. This is challenging as it requires (a) exploring goals of increasing difficulty, while ensuring that the agent (b) is exposed to a diverse set of goals in a sample efficient manner and (c) does not catastrophically forget previously solved goals. We propose Curriculum Self Play (CuSP), an automated goal generation framework that seeks to satisfy these desiderata by virtue of a multi-player game with four agents. We extend the asymmetric curricula learning in PAIRED (Dennis et al., 2020) to a symmetrized game that carefully balances cooperation and competition between two off-policy student learners and two regret-maximizing teachers. CuSP additionally introduces entropic goal coverage and accounts for the non-stationary nature of the students, allowing us to automatically induce a curriculum that balances progressive exploration with anti-catastrophic exploitation. We demonstrate that our method succeeds at generating an effective curricula of goals for a range of control tasks, outperforming other methods at zero-shot test-time generalization to novel out-of-distribution goals.

8. ICLR

   Frame averaging for invariant and equivariant network design

   Omri Puny, Matan Atzmon, Heli Ben-Hamu, Edward J Smith, Ishan Misra, Aditya Grover, and Yaron Lipman

   In International Conference on Learning Representations (ICLR), 2022

   Abs PDF Code

   Many machine learning tasks involve learning functions that are known to be invariant or equivariant to certain symmetries of the input data. However, it is often challenging to design neural network architectures that respect these symmetries while being expressive and computationally efficient. For example, Euclidean motion invariant/equivariant graph or point cloud neural networks. We introduce Frame Averaging (FA), a general purpose and systematic framework for adapting known (backbone) architectures to become invariant or equivariant to new symmetry types. Our framework builds on the well known group averaging operator that guarantees invariance or equivariance but is intractable. In contrast, we observe that for many important classes of symmetries, this operator can be replaced with an averaging operator over a small subset of the group elements, called a frame. We show that averaging over a frame guarantees exact invariance or equivariance while often being much simpler to compute than averaging over the entire group. Furthermore, we prove that FA-based models have maximal expressive power in a broad setting and in general preserve the expressive power of their backbone architectures. Using frame averaging, we propose a new class of universal Graph Neural Networks (GNNs), universal Euclidean motion invariant point cloud networks, and Euclidean motion invariant Message Passing (MP) GNNs. We demonstrate the practical effectiveness of FA on several applications including point cloud normal estimation, beyond 2-WL graph separation, and n-body dynamics prediction, achieving state-of-the-art results in all of these benchmarks.

9. AAAI

   Pretrained transformers as universal computation engines

   Kevin Lu, Aditya Grover, Pieter Abbeel, and Igor Mordatch

   In AAAI Conference on Artificial Intelligence, 2022

   Abs PDF

   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. We consider such a model, which we call a Frozen Pretrained Transformer (FPT), and study finetuning it on a variety of sequence classification tasks spanning numerical computation, vision, and protein fold prediction. In contrast to prior works which investigate finetuning on the same modality as the pretraining dataset, we show that pretraining on natural language can improve performance and compute efficiency on non-language downstream tasks. Additionally, we perform an analysis of the architecture, comparing the performance of a random initialized transformer to a random LSTM. Combining the two insights, we find language-pretrained transformers can obtain strong performance on a variety of non-language tasks.

2021

1. NeurIPS

   Moser flow: Divergence-based generative modeling on manifolds

   Noam Rozen, Aditya Grover, Maximilian Nickel, and Yaron Lipman

   Advances in Neural Information Processing Systems (NeurIPS), 2021

   PDF
   Outstanding Paper Award
2. NeurIPS

   BCD nets: Scalable variational approaches for bayesian causal discovery

   Chris Cundy, Aditya Grover, and Stefano Ermon

   Advances in Neural Information Processing Systems (NeurIPS), 2021

   PDF
3. NeurIPS

   Pirank: Scalable learning to rank via differentiable sorting

   Robin Swezey, Aditya Grover, Bruno Charron, and Stefano Ermon

   Advances in Neural Information Processing Systems (NeurIPS), 2021

   PDF
4. NeurIPS

   Decision transformer: Reinforcement learning via sequence modeling

   Lili Chen, Kevin Lu, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Misha Laskin, Pieter Abbeel, Aravind Srinivas, and Igor Mordatch

   Advances in Neural Information Processing Systems (NeurIPS), 2021

   PDF
5. Joule

   Bayesian learning for rapid prediction of lithium-ion battery-cycling protocols

   Benben Jiang, William E Gent, Fabian Mohr, Supratim Das, Marc D Berliner, Michael Forsuelo, Hongbo Zhao, Peter M Attia, Aditya Grover, Patrick K Herring, and  others

   Joule, 2021

   PDF
6. ICLR

   Anytime sampling for autoregressive models via ordered autoencoding

   Yilun Xu, Yang Song, Sahaj Garg, Linyuan Gong, Rui Shu, Aditya Grover, and Stefano Ermon

   2021

   PDF
7. ICLR

   Reset-free lifelong learning with skill-space planning

   Kevin Lu, Aditya Grover, Pieter Abbeel, and Igor Mordatch

   2021

   PDF
8. AISTATS

   Learning from an Exploring Demonstrator: Optimal Reward Estimation for Bandits

   Wenshuo Guo, Kumar Krishna Agrawal, Aditya Grover, Vidya Muthukumar, and Ashwin Pananjady

   In International Conference on Artificial Intelligence and Statistics (AISTATS), 2021

   PDF

2020

1. Nature

   Closed-loop optimization of extreme fast charging for batteries using machine learning

   Peter Attia, Aditya Grover, Norman Jin, Kristen Severson, Bryan Cheong, Jerry Liao, Michael H Chen, Nicholas Perkins, Zi Yang, Patrick Herring, Muratahan Aykol, Stephen Harris, Richard Braatz, Stefano Ermon, and William Chueh

   Nature, 2020

   PDF
2. ICML

   Fair Generative Modeling via Weak Supervision

   Kristy Choi, Aditya Grover, Trisha Singh, Rui Shu, and Stefano Ermon

   In International Conference on Machine Learning (ICML), 2020

   PDF
3. AISTATS

   Permutation Invariant Graph Generation via Score-Based Generative Modeling

   Chenhao Niu, Yang Song, Jiaming Song, Shengjia Zhao, Aditya Grover, and Stefano Ermon

   In International Conference on Artificial Intelligence and Statistics (AISTATS), 2020

   PDF
4. AAAI

   AlignFlow: Cycle Consistent Learning from Multiple Domains via Normalizing Flows

   Aditya Grover, Christopher Chute, Rui Shu, Zhangjie Cao, and Stefano Ermon

   In AAAI Conference on Artificial Intelligence, 2020

   PDF

2019

1. NeurIPS

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

   Aditya Grover, Jiaming Song, Alekh Agarwal, Kenneth Tran, Ashish Kapoor, Eric Horvitz, and Stefano Ermon

   In Advances in Neural Information Processing Systems (NeurIPS), 2019
2. ICML

   Graphite: Iterative generative modeling of graphs

   Aditya Grover, Aaron Zweig, and Stefano Ermon

   In International Conference on Machine Learning (ICML), 2019
3. ICML

   Neural Joint Source-Channel Coding

   Kristy Choi, Kedar Tatwawadi, Aditya Grover, Tsachy Weissman, and Stefano Ermon

   In International Conference on Machine Learning (ICML), 2019
4. ICLR

   Stochastic Optimization of Sorting Networks via Continuous Relaxations

   Aditya Grover, Eric Wang, Aaron Zweig, and Stefano Ermon

   In International Conference on Learning Representations (ICLR), 2019
5. AISTATS

   Uncertainty Autoencoders: Learning Compressed Representations via Variational Information Maximization

   Aditya Grover, and Stefano Ermon

   In International Conference on Artificial Intelligence and Statistics (AISTATS), 2019
6. AISTATS

   Learning Controllable Fair Representations

   Jiaming Song, Pratyusha Kalluri, Aditya Grover, Shengjia Zhao, and Stefano Ermon

   In International Conference on Artificial Intelligence and Statistics (AISTATS), 2019

2018

1. NeurIPS

   Streamlining variational inference for constraint satisfaction problems

   Aditya Grover, Tudor Achim, and Stefano Ermon

   In Advances in Neural Information Processing Systems (NeurIPS), 2018
2. ICML

   Learning Policy Representations in Multiagent Systems

   Aditya Grover, Maruan Al-Shedivat, Jayesh K Gupta, Yura Burda, and Harrison Edwards

   In International Conference on Machine Learning (ICML), 2018
3. ICML

   Modeling sparse deviations for compressed sensing using generative models

   Manik Dhar, Aditya Grover, and Stefano Ermon

   In International Conference on Machine Learning (ICML), 2018
4. AISTATS

   Best arm identification in multi-armed bandits with delayed feedback

   Aditya Grover, Todor Markov, Peter Attia, Norman Jin, Nicholas Perkins, Bryan Cheong, Michael Chen, Zi Yang, Stephen Harris, William Chueh, and Stefano Ermon

   In International Conference on Artificial Intelligence and Statistics (AISTATS), 2018
5. AISTATS

   Variational Rejection Sampling

   Aditya Grover, Ramki Gummadi, Miguel Lazaro-Gredilla, Dale Schuurmans, and Stefano Ermon

   In International Conference on Artificial Intelligence and Statistics (AISTATS), 2018
6. AAMAS

   Evaluating Generalization in Multiagent Systems using Agent-Interaction Graphs

   Aditya Grover, Maruan Al-Shedivat, Jayesh K Gupta, Yuri Burda, and Harrison Edwards

   In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2018
7. AAAI

   Boosted generative models

   Aditya Grover, and Stefano Ermon

   In AAAI Conference on Artificial Intelligence, 2018
8. AAAI

   Flow-GAN: Combining maximum likelihood and adversarial learning in generative models

   Aditya Grover, Manik Dhar, and Stefano Ermon

   In AAAI Conference on Artificial Intelligence, 2018

2016

1. NeurIPS

   Variational Bayes on Monte Carlo Steroids

   Aditya Grover, and Stefano Ermon

   In Advances in Neural Information Processing Systems (NeurIPS), 2016
2. KDD

   node2vec: Scalable Feature Learning for Networks

   Aditya Grover, and Jure Leskovec

   In International Conference on Knowledge Discovery and Data Mining (KDD), 2016
3. IJCAI

   Contextual Symmetries in Probabilistic Graphical Models

   Ankit Anand, Aditya Grover,  Mausam, and Parag Singla

   In International Joint Conference on Artificial Intelligence (IJCAI), 2016

2015

1. KDD

   A deep hybrid model for weather forecasting

   Aditya Grover, Ashish Kapoor, and Eric Horvitz

   In International Conference on Knowledge Discovery and Data Mining (KDD), 2015
2. IJCAI

   ASAP-UCT: abstracttraction of state-action pairs in UCT

   Ankit Anand, Aditya Grover,  Mausam, and Parag Singla

   In International Joint Conference on Artificial Intelligence (IJCAI), 2015
3. AAMAS

   A Novel abstracttraction Framework for Online Planning

   Ankit Anand, Aditya Grover,  Mausam, and Parag Singla

   In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2015