Department of Computer Science and Engineering

Indian Institute of Technology Hyderabad (IITH) is a premier institute of science and technology established in 2008. IITH has been consistently ranked in the&nbsp;<a href="https://iith.ac.in/reports/" rel="noopener noreferrer">top 10 institutes</a>&nbsp;in India for Engineering&nbsp;<a href="https://www.nirfindia.org/2021/EngineeringRanking.html" rel="noopener noreferrer" target="_blank">according to NIRF</a>&nbsp;making it one of the most coveted schools for science and technology in the country.

IITH offers&nbsp;<a href="https://iith.ac.in/academics/under-graduate/">undergraduate programs</a>&nbsp;in all the classical engineering disciplines, applied sciences, design, as well as several modern interdisciplinary areas. Students are given a flexibility to explore a broad set of areas, and potentially pursue a minor or double major in a discipline that is not their own. Students who wish to seek a deeper understanding of their own discipline are strongly encouraged to get involved in cutting-edge research with the help of a faculty to mentor them, and earn an Honors in their own field.

The very foundation of IIT Hyderabad is based on&nbsp;<a href="https://iith.ac.in/research/">research and innovation</a>. The vibrant research culture is evident from the number of patents and publications that IITH produces consistently every year. IITH offers&nbsp;<a href="https://iith.ac.in/academics/programmes-offered/">graduate programs</a>&nbsp;at both a masters, and a doctoral level, in several diverse areas. There are separate programs for technology, design, science, and liberal arts. The&nbsp;<a href="https://iith.ac.in/academics/post-graduate/">MTech program</a>&nbsp;is offered in various modes and durations to cater to the ever-growing need of postgraduate level professionals in the country.

IITH encourages and supports&nbsp;<a href="https://iic-iith.netlify.app/index.html" rel="noopener noreferrer" target="_blank">innovation and entrepreneurship</a>&nbsp;at every stage. The minor program in entrepreneurship is open to all students of IITH, and many of the courses are offered by industrialists who are entrepreneurs themselves. There are various&nbsp;<a href="https://iith.ac.in/research/centres-incubators/">innovation centers and incubators</a>&nbsp;that promote entrepreneurship and help mentor young innovators. IITH has been very successful in building tie-ups with leading academic institutions around the globe.

IITH enjoys a very special relationship with Japanese universities and industries that goes beyond academic and research collaborations. In fact, some of the iconic buildings in IITH campus will carry the signature of Japanese architecture.

IITH creates a unique holistic ecosystem for education that offers interactive learning, a very flexible academic structure, cutting-edge research, strong industry collaboration, and entrepreneurship. This is an environment which enables students and faculty to translate their dreams into realities.

IIT Hyderabad

Department of Artificial Intelligence

Generative Adversarial Networks (GANs) have swiftly evolved to imitate increasingly complex image distributions. However, majority of the developments focus on performance of GANs on balanced datasets. We find that the existing GANs and their training regimes which work well on balanced datasets fail to be effective in case of imbalanced (i.e. long-tailed) datasets. In this work we introduce a novel theoretically motivated Class Balancing regularizer for training GANs. Our regularizer makes use of the knowledge from a pretrained classifier to ensure balanced learning of all the classes in the dataset. This is achieved via modelling the effective class frequency based on the exponential forgetting observed in neural networks and encouraging the GAN to focus on underrepresented classes. We demonstrate the utility of our regularizer in learning representations for long-tailed distributions via achieving better performance than existing approaches over multiple datasets. Specifically, when applied to an unconditional GAN, it improves the FID from 13.03 to 9.01 on the long-tailed iNaturalist-2019 dataset. © 2021 37th Conference on Uncertainty in Artificial Intelligence, UAI 2021. All Rights Reserved.

World University root node

37th Conference on Uncertainty in Artificial Intelligence, UAI 2021

Class Balancing GAN with a Classifier in the Loop

Pipe-sticking during drilling operations causes severe difficulties, including economic losses and safety issues. Therefore, real-time stuck-pipe predictions are an important tool to preempt this problem and avoid the aforementioned troubles. In this study, we have developed a prediction technique based on artificial intelligence, in collaboration with industry, the government, and academia. This technique was developed by combining an unsupervised learning model built using an encoder-decoder, long short-term memory architecture, with a relative error function. The model was trained with the time series data of normal drilling operations and based on an important hypothesis: reconstruction errors between observed and predicted values are higher around the time of pipe sticking than during normal drilling operations. An evaluation method of stuck-pipe possibilities using a relative error function reduced false predictors caused by large variations of drilling parameters. The prediction technique was then applied to 34 actual stuck-pipe events, where it was found that reconstruction errors calculated with the relative error function increased 0.5-10 hours prior to the pipe sticking for 17 out of 34 stuck-pipe events (thereby partly confirming our hypothesis). © Copyright 2021, Society of Petroleum Engineers

Society of Petroleum Engineers - Abu Dhabi International Petroleum Exhibition and Conference, ADIP 2021

Approach for Real-Time Prediction of Pipe Stuck Risk Using a Long Short-Term Memory Autoencoder Architecture

We study an interesting variant of the stochastic multi-armed bandit problem, which we call the Fair-MAB problem, where, in addition to the objective of maximizing the sum of expected rewards, the algorithm also needs to ensure that at any time, each arm is pulled at least a pre-specified fraction of times. We investigate the interplay between learning and fairness in terms of a pre-specified vector denoting the fractions of guaranteed pulls. We define a fairness-aware regret, which we call r-Regret, that takes into account the above fairness constraints and extends the conventional notion of regret in a natural way. Our primary contribution is to obtain a complete characterization of a class of Fair-MAB algorithms via two parameters: The unfairness tolerance and the learning algorithm used as a black-box. For this class of algorithms, we provide a fairness guarantee that holds uniformly over time, irrespective of the chosen learning algorithm. Further, when the learning algorithm is UCB1, we show that our algorithm achieves constant r-Regret for a large enough time horizon. Finally, we analyze the cost of fairness in terms of the conventional notion of regret. We conclude by experimentally validating our theoretical results. © 2021 Vishakha Patil, Ganesh Ghalme, Vineet Nair, Y. Narahari.

Journal of Machine Learning Research

Achieving fairness in the stochastic multi-armed bandit problem

As the state-of-the-art machine learning methods in many fields rely on larger datasets, storing datasets and training models on them become significantly more expensive. This paper proposes a training set synthesis technique for data-efficient learning, called Dataset Condensation, that learns to condense large dataset into a small set of informative synthetic samples for training deep neural networks from scratch. We formulate this goal as a gradient matching problem between the gradients of deep neural network weights that are trained on the original and our synthetic data. We rigorously evaluate its performance in several computer vision benchmarks and demonstrate that it significantly outperforms the state-of-the-art methods. Finally we explore the use of our method in continual learning and neural architecture search and report promising gains when limited memory and computations are available. © 2021 ICLR 2021 - 9th International Conference on Learning Representations. All rights reserved.

ICLR 2021 - 9th International Conference on Learning Representations

DATASET CONDENSATION WITH GRADIENT MATCHING

In this paper, we introduce ballooning multi-armed bandits (BL-MAB), a novel extension of the classical stochastic MAB model. In the BL-MAB model, the set of available arms grows (or balloons) over time. In contrast to the classical MAB setting where the regret is computed with respect to the best arm overall, the regret in a BL-MAB setting is computed with respect to the best available arm at each time. We first observe that the existing stochastic MAB algorithms result in linear regret for the BL-MAB model. We prove that, if the best arm is equally likely to arrive at any time instant, a sub-linear regret cannot be achieved. Next, we show that if the best arm is more likely to arrive in the early rounds, one can achieve sub-linear regret. Our proposed algorithm determines (1) the fraction of the time horizon for which the newly arriving arms should be explored and (2) the sequence of arm pulls in the exploitation phase from among the explored arms. Making reasonable assumptions on the arrival distribution of the best arm in terms of the thinness of the distribution's tail, we prove that the proposed algorithm achieves sub-linear instance-independent regret. We further quantify explicit dependence of regret on the arrival distribution parameters. We reinforce our theoretical findings with extensive simulation results. We conclude by showing that our algorithm would achieve sub-linear regret even if (a) the distributional parameters are not exactly known, but are obtained using a reasonable learning mechanism or (b) the best arm is not more likely to arrive early, but a large fraction of arms is likely to arrive relatively early. © 2021 Elsevier B.V.

Fulltext

Artificial Intelligence

Ballooning multi-armed bandits

Pipe-sticking during drilling operations causes severe difficulties, including economic losses and safety issues. Therefore, stuck-pipe predictions are an important tool to preempt this problem and avoid the aforementioned troubles. In this study, we have developed a prediction technique based on artificial intelligence, in collaboration with industry, the government, and academia. This technique was an unsupervised learning model built using an encoder-decoder, long short-term memory architecture. The model was trained with the time series data of normal drilling operations and based on an important hypothesis: reconstruction errors between observed and predicted values are higher around the time of pipe sticking than during normal drilling operations. The trained model was then applied to 34 actual stuck-pipe events, where it was found that reconstruction errors increased prior to the pipe sticking in some cases (thereby partly confirming our hypothesis) and were sensitive to large variations in the drilling parameters. © 2021, Society of Petroleum Engineers.

Society of Petroleum Engineers - SPE/IATMI Asia Pacific Oil and Gas Conference and Exhibition 2021, APOG 2021

An unsupervised learning model for pipe stuck predictions using a long short-term memory autoencoder architecture

Generative Adversarial Networks (GANs) have swiftly evolved to imitate increasingly complex image distributions. However, majority of the developments focus on performance of GANs on balanced datasets. We find that the existing GANs and their training regimes which work well on balanced datasets fail to be effective in case of imbalanced (i.e. long-tailed) datasets. In this work we introduce a novel theoretically motivated Class Balancing regularizer for training GANs. Our regularizer makes use of the knowledge from a pretrained classifier to ensure balanced learning of all the classes in the dataset. This is achieved via modelling the effective class frequency based on the exponential forgetting observed in neural networks and encouraging the GAN to focus on underrepresented classes. We demonstrate the utility of our regularizer in learning representations for long-tailed distributions via achieving better performance than existing approaches over multiple datasets. Specifically, when applied to an unconditional GAN, it improves the FID from 13.03 to 9.01 on the long-tailed iNaturalist-2019 dataset. © 2021 Proceedings of Machine Learning Research. All Rights Reserved.

Proceedings of Machine Learning Research

Strategic classification studies the interaction between a classification rule and the strategic agents it governs. Under the assumption that the classifier is known, rational agents respond to it by manipulating their features. However, in many real-life scenarios of high-stake classification (e.g., credit scoring), the classifier is not revealed to the agents, which leads agents to attempt to learn the classifier and game it too. In this paper we generalize the strategic classification model to such scenarios. We define the “price of opacity” as the difference in prediction error between opaque and transparent strategy-robust classifiers, characterize it, and give a sufficient condition for this price to be strictly positive, in which case transparency is the recommended policy. Our experiments show how Hardt et al.'s robust classifier is affected by keeping agents in the dark. Copyright © 2021 by the author(s)

Strategic Classification in the Dark

Recent advancements in CNNs have shown remarkable achievements in various CV/AI applications. Though CNNs show near human or better than human performance in many critical tasks, they are quite vulnerable to adversarial attacks. These attacks are potentially dangerous in real-life deployments. Though there have been many adversarial attacks proposed in recent years, there is no proper way of quantifying the effectiveness of these attacks. As of today, mere fooling rate is used for measuring the susceptibility of the models, or the effectiveness of adversarial attacks. Fooling rate just considers label flipping and does not consider the cost of such flipping, for instance, in some deployments, flipping between two species of dogs may not be as severe as confusing a dog category with that of a vehicle. Therefore, the metric to quantify the vulnerability of the models should capture the severity of the flipping as well. In this work we first bring out the drawbacks of the existing evaluation and propose novel metrics to capture various aspects of the fooling. Further, for the first time, we present a comprehensive analysis of several important adversarial attacks over a set of distinct CNN architectures. We believe that the presented analysis brings valuable insights about the current adversarial attacks and the CNN models. © 2020 IEEE.

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

Adversarial fooling beyond "flipping the label"

We describe an integrated theory of olfactory systems operation that incorporates experimental findings across scales, stages, and methods of analysis into a common framework. In particular, we consider the multiple stages of olfactory signal processing as a collective system, in which each stage samples selectively from its antecedents. We propose that, following the signal conditioning operations of the nasal epithelium and glomerular-layer circuitry, the plastic external plexiform layer of the olfactory bulb effects a process of category learning—the basis for extracting meaningful, quasi-discrete odor representations from the metric space of undifferentiated olfactory quality. Moreover, this early categorization process also resolves the foundational problem of how odors of interest can be recognized in the presence of strong competitive interference from simultaneously encountered background odorants. This problem is fundamentally constraining on early-stage olfactory encoding strategies and must be resolved if these strategies and their underlying mechanisms are to be understood. Multiscale general theories of olfactory systems operation are essential in order to leverage the analytical advantages of engineered approaches together with our expanding capacity to interrogate biological systems. © Copyright © 2020 Cleland and Borthakur.