IIT Madras is a public technical and research university located in Chennai, Tamil Nadu. Founded in 1959, it is recognised as an Institute of National Importance.

IIT Madras has been ranked as the top engineering institute in India for four years in a row by the National Institutional Ranking Framework of the MHRD

It currently offers undergraduate, postgraduate and research degrees across 16 disciplines in Engineering, Sciences, Humanities and Management. About 596 faculty belonging to science and engineering departments and centres of the Institute are engaged in teaching, research and industrial consultancy.

IIT Madras

PMMA flames are used as surrogate fuels for fire studies. Horizontal slab PMMA flame is studied here in laminar conditions. In particular, the CH radical field is obtained in a qualitative manner with respect to the luminous flame. CH-PLIF was used to obtain the CH radical field, along with simultaneous imaging of the flame luminosity. This was done at various time instances after ignition, and the change in flame shape and the CH field was observed. It was found that CH field was present in the same zone as the luminous flame. Since the luminosity is due to black body emission from the soot, it can be seen that the CH radicals exist in the same region as the soot region in the PMMA flames. This information along with OH radical field information will be useful for validating computational models for fire prediction. © 2021, Springer Nature Singapore Pte Ltd.

Department of Aerospace Engineering

World University root node

Department of Computer Science and Engineering

NCICEC 2019: Advances in IC Engines and Combustion Technology

CH-PLIF in Horizontal Slab PMMA Laminar Flame

The F-measure is a widely used performance measure for multi-label classification, where multiple labels can be active in an instance simultaneously (e.g. in image tagging, multiple tags can be active in any image). In particular, the F-measure explicitly balances recall (fraction of active labels predicted to be active) and precision (fraction of labels predicted to be active that are actually so), both of which are important in evaluating the overall performance of a multi-label classifier. As with most discrete prediction problems, however, directly optimizing the F-measure is computationally hard. In this paper, we explore the question of designing convex surrogate losses that are calibrated for the F-measure specifically, that have the property that minimizing the surrogate loss yields (in the limit of sufficient data) a Bayes optimal multi-label classifier for the F-measure. We show that the F-measure for an s-label problem, when viewed as a 2s × 2s loss matrix, has rank at most s2 + 1, and apply a result of Ramaswamy et al. (2014) to design a family of convex calibrated surrogates for the F-measure. The resulting surrogate risk minimization algorithms can be viewed as decomposing the multi-label F-measure learning problem into s2 + 1 binary class probability estimation problems. We also provide a quantitative regret transfer bound for our surrogates, which allows any regret guarantees for the binary problems to be transferred to regret guarantees for the overall F-measure problem, and discuss a connection with the algorithm of Dembczynski et al. (2013). Our experiments confirm our theoretical findings. © 2020 by the Authors All rights reserved.

37th International Conference on Machine Learning, ICML 2020

Convex calibrated surrogates for the multi-label f-measure

In response to recent criticism of gradient-based visualization techniques, we propose a new methodology to generate visual explanations for deep Convolutional Neural Networks (CNN) - based models. Our approach - Ablation-based Class Activation Mapping (Ablation CAM) uses ablation analysis to determine the importance (weights) of individual feature map units w.r.t. class. Further, this is used to produce a coarse localization map highlighting the important regions in the image for predicting the concept. Our objective and subjective evaluations show that this gradient-free approach works better than state-of-the-art Grad-CAM technique. Moreover, further experiments are carried out to show that Ablation-CAM is class discriminative as well as can be used to evaluate trust in a model. © 2020 IEEE.

Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020

Ablation-CAM: Visual explanations for deep convolutional network via gradient-free localization

Recent advances in Question Answering have lead to the development of very complex models which compute rich representations for query and documents by capturing all pairwise interactions between query and document words. This makes these models expensive in space and time, and in practice one has to restrict the length of the documents that can be fed to these models. Such models have also been recently employed for the task of predicting dialog responses from available background documents (e.g., Holl-E dataset). However, here the documents are longer, thereby rendering these complex models infeasible except in select restricted settings. In order to overcome this, we use standard simple models which do not capture all pairwise interactions, but learn to emulate certain characteristics of a complex teacher network. Specifically, we first investigate the conicity of representations learned by a complex model and observe that it is significantly lower than that of simpler models. Based on this insight, we modify the simple architecture to mimic this characteristic. We go further by using knowledge distillation approaches, where the simple model acts as a student and learns to match the output from the complex teacher network. We experiment with the Holl-E dialog data set and show that by mimicking characteristics and matching outputs from a teacher, even a simple network can give improved performance. © 2019 Association for Computational Linguistics

NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference

On knowledge distillation from complex networks for response prediction

Converting an n-dimensional vector to a probability distribution over n objects is a commonly used component in many machine learning tasks like multiclass classification, multilabel classification, attention mechanisms etc. For this, several probability mapping functions have been proposed and employed in literature such as softmax, sum-normalization, spherical softmax, and sparsemax, but there is very little understanding in terms how they relate with each other. Further, none of the above formulations offer an explicit control over the degree of sparsity. To address this, we develop a unified framework that encompasses all these formulations as special cases. This framework ensures simple closed-form solutions and existence of sub-gradients suitable for learning via backpropagation. Within this framework, we propose two novel sparse formulations, sparsegen-lin and sparsehourglass, that seek to provide a control over the degree of desired sparsity. We further develop novel convex loss functions that help induce the behavior of aforementioned formulations in the multilabel classification setting, showing improved performance. We also demonstrate empirically that the proposed formulations, when used to compute attention weights, achieve better or comparable performance on standard seq2seq tasks like neural machine translation and abstractive summarization. © 2018 Curran Associates Inc.All rights reserved.

Advances in Neural Information Processing Systems

On controllable sparse alternatives to softmax

We consider the problem of n-class classification (n ≥ 2), where the classifier can choose to abstain from making predictions at a given cost, say, a factor α of the cost of misclassification. Our goal is to design consistent algorithms for such n-class classification problems with a ‘reject option’; while such algorithms are known for the binary (n = 2) case, little has been understood for the general multiclass case. We show that the well known Crammer-Singer surrogate and the one-vs-all hinge loss, albeit with a different predictor than the standard argmax, yield consistent algorithms for this problem when α = ½. More interestingly, we design a new convex surrogate, which we call the binary encoded predictions surrogate, that is also consistent for this problem when α = ½ and operates on a much lower dimensional space (log(n) as opposed to n). We also construct modified versions of all these three surrogates to be consistent for any given α ∈ [0, ½]. © 2018, Institute of Mathematical Statistics. All rights reserved.

Fulltext

Electronic Journal of Statistics

Consistent algorithms for multiclass classification with an abstain option

The F-measure and its variants are performance measures of choice for evaluating classification and retrieval tasks in the presence of severe class imbalance. It is thus highly desirable to be able to directly optimize these performance measures on large-scale data. Recent advances have shown that this is possible in the simple binary classification setting. However, scant progress exists in multiclass settings with a large number of classes where, in addition, class-imbalance is much more severe. The lack of progress is especially conspicuous for the macro-Averaged F-measure, which is the widely preferred Fmeasure variant in multiclass settings due to its equal emphasis on rare classes. Known methods of optimization scale poorly for macro F-measure, often requiring run times that are exponential in the number of classes. We develop BEAM-F, the first efficient method for directly optimizing the macro F-measure in multiclass settings. The challenge here is the intractability of optimizing a sum of fractional-linear functions over the space of confusion matrices. We overcome this difficulty by formulating the problem as a biconcave maximization program and solve it using an efficient alternating maximization approach that involves a Frank- Wolfe based iterative solver. Our approach offers guaranteed convergence to a stationary point and experiments show that, for a range synthetic data sets and real-world applications, our method offers superior performance on problems exhibiting large class imbalance. © 2016 IEEE.

Department of Applied Mechanics

Proceedings - IEEE International Conference on Data Mining, ICDM

Optimizing the multiclass F-measure via biconcave programming

Mixture proportion estimation (MPE) is the problem of estimating the weight of a component distribution in a mixture, given samples from the mixture and component. This problem constitutes a key part in many "weakly supervised learning" problems like learning with positive and unlabelled samples, learning with label noise, anomaly detection and crowdsourcing. While there have been several methods proposed to solve this problem, to the best of our knowledge no efficient algorithm with a proven convergence rate towards the true proportion exists for this problem. We fill this gap by constructing a provably correct algorithm for MPE, and derive convergence rates under certain assumptions on the distribution. Our method is based on embedding distributions onto an RKHS, and implementing it only requires solving a simple convex quadratic programming problem a few times. We run our algorithm on several standard classification datasets, and demonstrate that it performs comparably to or better than other algorithms on most datasets. Copyright © 2016 by the author(s).

33rd International Conference on Machine Learning, ICML 2016

Mixture proportion estimation via kernel embedding of distributions

We study consistency properties of surrogate loss functions for general multiclass learning problems, defined by a general multiclass loss matrix. We extend the notion of classification calibration, which has been studied for binary and multiclass 0-1 classification problems (and for certain other specific learning problems), to the general multiclass setting, and derive necessary and sufficient conditions for a surrogate loss to be calibrated with respect to a loss matrix in this setting. We then introduce the notion of convex calibration dimension of a multiclass loss matrix, which measures the smallest 'size' of a prediction space in which it is possible to design a convex surrogate that is calibrated with respect to the loss matrix. We derive both upper and lower bounds on this quantity, and use these results to analyze various loss matrices. In particular, we apply our framework to study various subset ranking losses, and use the convex calibration dimension as a tool to show both the existence and non-existence of various types of convex calibrated surrogates for these losses. Our results strengthen recent results of Duchi et al. (2010) and Calauzènes et al. (2012) on the non-existence of certain types of convex calibrated surrogates in subset ranking. We anticipate the convex calibration dimension may prove to be a useful tool in the study and design of surrogate losses for general multiclass learning problems. ©2016 Harish G. Ramaswamy and Shivani Agarwal.

Journal of Machine Learning Research

Convex calibration dimension for multiclass loss matrices

This paper presents new consistent algorithms for multiclass learning with complex performance measures, defined by arbitrary functions of the confusion matrix. This setting includes as a special case all loss-based performance measures, which are simply linear functions of the confusion matrix, but also includes more complex performance measures such as the multi-class G-mean and micro F1 measures. We give a general framework for designing consistent algorithms for such performance measures by viewing the learning problem as an optimization problem over the set of feasible confusion matrices, and give two specific instantiations based on the Frank-Wolfe method for concave performance measures and on the bisection method for ratio-of-linear performance measures. The resulting algorithms are provably consistent and outperform a multiclass version of the state-of-the-art SVMperf method in experiments; for large multiclass problems, the algorithms are also orders of magnitude faster than SVMperf. © Copyright 2015 by International Machine Learning Society (IMLS). All rights reserved.

32nd International Conference on Machine Learning, ICML 2015

Consistent multiclass algorithms for complex performance measures

Hierarchical classification problems are multi-class supervised learning problems with a predefined hierarchy over the set of class labels. In this work, we study the consistency of hierarchical classification algorithms with respect to a natural loss, namely the tree distance metric on the hierarchy tree of class labels, via the usage of calibrated surrogates. We first show that the Bayes optimal classifier for this loss classifies an instance according to the deepest node in the hierarchy such that the total conditional probability of the subtree rooted at the node is greater than 1\2. We exploit this insight to develop new consistent algorithm for hierarchical classification, that makes use of an algorithm known to be consistent for the "multiclass classification with reject option (MCRO)" problem as a subroutine. Our experiments on a number of benchmark datasets show that the resulting algorithm, which we term OvA-Cascade, gives improved performance over other state-of-the-art hierarchical classification algorithms. © Copyright 2015 by International Machine Learning Society (IMLS). All rights reserved.

Convex calibrated surrogates for hierarchical classification

A popular approach to solving multiclass learning problems is to reduce them to a set of binary classification problems through some output code matrix: the widely used one-vs-all and all-pairs methods, and the error-correcting output code methods of Dietterich and Bakiri (1995), can all be viewed as special cases of this approach. In this paper, we consider the question of statistical consistency of such methods. We focus on settings where the binary problems are solved by minimizing a binary surrogate loss, and derive general conditions on the binary surrogate loss under which the one-vs-all and all-pairs code matrices yield consistent algorithms with respect to the multiclass 0-1 loss. We then consider general multiclass learning problems defined by a general multiclass loss, and derive conditions on the output code matrix and binary surrogates under which the resulting algorithm is consistent with respect to the target multiclass loss. We also consider probabilistic code matrices, where one reduces a multiclass problem to a set of class probability labeled binary problems, and show that these can yield benefits in the sense of requiring a smaller number of binary problems to achieve overall consistency. Our analysis makes interesting connections with the theory of proper composite losses (Buja et al., 2005; Reid and Williamson, 2010); these play a role in constructing the right 'decoding' for converting the predictions on the binary problems to the final multiclass prediction. To our knowledge, this is the first work that comprehensively studies consistency properties of output code based methods for multiclass learning. © 2014 H.G. Ramaswamy, B.S. Babu, S. Agarwal & R.C. Williamson.

On the consistency of output code based learning algorithms for multiclass learning problems

The design of convex, calibrated surrogate losses, whose minimization entails consistency with respect to a desired target loss, is an important concept to have emerged in the theory of machine learning in recent years. We give an explicit construction of a convex least-squares type surrogate loss that can be designed to be calibrated for any multiclass learning problem for which the target loss matrix has a low-rank structure; the surrogate loss operates on a surrogate target space of dimension at most the rank of the target loss. We use this result to design convex calibrated surrogates for a variety of subset ranking problems, with target losses including the precision@q, expected rank utility, mean average precision, and pairwise disagreement.

Convex calibrated surrogates for low-rank loss matrices with applications to subset ranking losses

We study consistency properties of surrogate loss functions for general multiclass classification problems, defined by a general loss matrix. We extend the notion of classification calibration, which has been studied for binary and multiclass 0-1 classification problems (and for certain other specific learning problems), to the general multiclass setting, and derive necessary and sufficient conditions for a surrogate loss to be classification calibrated with respect to a loss matrix in this setting. We then introduce the notion of classification calibration dimension of a multiclass loss matrix, which measures the smallest 'size' of a prediction space for which it is possible to design a convex surrogate that is classification calibrated with respect to the loss matrix. We derive both upper and lower bounds on this quantity, and use these results to analyze various loss matrices. In particular, as one application, we provide a different route from the recent result of Duchi et al. (2010) for analyzing the difficulty of designing 'low-dimensional' convex surrogates that are consistent with respect to pairwise subset ranking losses. We anticipate the classification calibration dimension may prove to be a useful tool in the study and design of surrogate losses for general multiclass learning problems.

Classification calibration dimension for general multiclass losses

Cracks induced due to fretting at the edge of contact between blade and disk in turbomachinery have been identified as a possible cause for a number of aircraft-engine hardware failures. Fretting is a frictional contact phenomenon that leads to damage at the contact region between two nominally-clamped surfaces subjected to oscillatory motion of small amplitudes. The contact stresses that drive the crack nucleation are very sensitive to the shape of the contacting surfaces and the coefficient of friction. The aim of the current effort is to characterize the effect of shape of the contacting profiles on the performance of components and to develop a mechanics based tool for life prediction. The effect of coefficient of friction on the contact problem has also been investigated.