Author name cluster

Rishabh K. Iyer

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

14 papers

2 author rows

ICML Conference 2024 Conference Paper

SCoRe: Submodular Combinatorial Representation Learning

Anay Majee
Suraj Kothawade
Krishnateja Killamsetty
Rishabh K. Iyer

In this paper we introduce the SCoRe ( S ubmodular Co mbinatorial Re presentation Learning) framework, a novel approach in representation learning that addresses inter-class bias and intra-class variance. SCoRe provides a new combinatorial viewpoint to representation learning, by introducing a family of loss functions based on set-based submodular information measures. We develop two novel combinatorial formulations for loss functions, using the Total Information and Total Correlation, that naturally minimize intra-class variance and inter-class bias. Several commonly used metric/contrastive learning loss functions like supervised contrastive loss, orthogonal projection loss, and N-pairs loss, are all instances of SCoRe, thereby underlining the versatility and applicability of SCoRe in a broad spectrum of learning scenarios. Novel objectives in SCoRe naturally model class-imbalance with up to 7. 6% improvement in classification on CIFAR-10-LT, CIFAR-100-LT, MedMNIST, 2. 1% on ImageNet-LT, and 19. 4% in object detection on IDD and LVIS (v1. 0), demonstrating its effectiveness over existing approaches.

Details

NeurIPS Conference 2024 Conference Paper

STONE: A Submodular Optimization Framework for Active 3D Object Detection

Ruiyu Mao
Sarthak K. Maharana
Rishabh K. Iyer
Yunhui Guo

3D object detection is fundamentally important for various emerging applications, including autonomous driving and robotics. A key requirement for training an accurate 3D object detector is the availability of a large amount of LiDAR-based point cloud data. Unfortunately, labeling point cloud data is extremely challenging, as accurate 3D bounding boxes and semantic labels are required for each potential object. This paper proposes a unified active 3D object detection framework, for greatly reducing the labeling cost of training 3D object detectors. Our framework is based on a novel formulation of submodular optimization, specifically tailored to the problem of active 3D object detection. In particular, we address two fundamental challenges associated with active 3D object detection: data imbalance and the need to cover the distribution of the data, including LiDAR-based point cloud data of varying difficulty levels. Extensive experiments demonstrate that our method achieves state-of-the-art performance with high computational efficiency compared to existing active learning methods. The code is available at https: //github. com/RuiyuM/STONE

PDF Details DOI

ICML Conference 2023 Conference Paper

Discrete Continuous Optimization Framework for Simultaneous Clustering and Training in Mixture Models

Parth Vipul Sangani
Arjun Shashank Kashettiwar
Pritish Chakraborty
Bhuvan Reddy Gangula
Durga Sivasubramanian
Ganesh Ramakrishnan
Rishabh K. Iyer
Abir De

We study a new framework of learning mixture models via automatic clustering called PRESTO, wherein we optimize a joint objective function on the model parameters and the partitioning, with each model tailored to perform well on its specific cluster. In contrast to prior work, we do not assume any generative model for the data. We convert our training problem to a joint parameter estimation cum a subset selection problem, subject to a matroid span constraint. This allows us to reduce our problem into a constrained set function minimization problem, where the underlying objective is monotone and approximately submodular. We then propose a new joint discrete-continuous optimization algorithm that achieves a bounded approximation guarantee for our problem. We show that PRESTO outperforms several alternative methods. Finally, we study PRESTO in the context of resource-efficient deep learning, where we train smaller resource-constrained models on each partition and show that it outperforms existing data partitioning and model pruning/knowledge distillation approaches, which in contrast to PRESTO, require large initial (teacher) models.

Details

ICML Conference 2022 Conference Paper

PLATINUM: Semi-Supervised Model Agnostic Meta-Learning using Submodular Mutual Information

Changbin Li
Suraj Kothawade
Feng Chen 0001
Rishabh K. Iyer

Few-shot classification (FSC) requires training models using a few (typically one to five) data points per class. Meta-learning has proven to be able to learn a parametrized model for FSC by training on various other classification tasks. In this work, we propose PLATINUM (semi-suPervised modeL Agnostic meTa learnIng usiNg sUbmodular Mutual information ), a novel semi-supervised model agnostic meta learning framework that uses the submodular mutual in- formation (SMI) functions to boost the perfor- mance of FSC. PLATINUM leverages unlabeled data in the inner and outer loop using SMI func- tions during meta-training and obtains richer meta- learned parameterizations. We study the per- formance of PLATINUM in two scenarios - 1) where the unlabeled data points belong to the same set of classes as the labeled set of a cer- tain episode, and 2) where there exist out-of- distribution classes that do not belong to the la- beled set. We evaluate our method on various settings on the miniImageNet, tieredImageNet and CIFAR-FS datasets. Our experiments show that PLATINUM outperforms MAML and semi- supervised approaches like pseduo-labeling for semi-supervised FSC, especially for small ratio of labeled to unlabeled samples.

Details

ICML Conference 2021 Conference Paper

GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training

Krishnateja Killamsetty
Durga Sivasubramanian
Ganesh Ramakrishnan
Abir De
Rishabh K. Iyer

The great success of modern machine learning models on large datasets is contingent on extensive computational resources with high financial and environmental costs. One way to address this is by extracting subsets that generalize on par with the full data. In this work, we propose a general framework, GRAD-MATCH, which finds subsets that closely match the gradient of the \emph{training or validation} set. We find such subsets effectively using an orthogonal matching pursuit algorithm. We show rigorous theoretical and convergence guarantees of the proposed algorithm and, through our extensive experiments on real-world datasets, show the effectiveness of our proposed framework. We show that GRAD-MATCH significantly and consistently outperforms several recent data-selection algorithms and achieves the best accuracy-efficiency trade-off. GRAD-MATCH is available as a part of the CORDS toolkit: \url{https: //github. com/decile-team/cords}.

Details

ICML Conference 2021 Conference Paper

Training Data Subset Selection for Regression with Controlled Generalization Error

Durga Sivasubramanian
Rishabh K. Iyer
Ganesh Ramakrishnan
Abir De

Data subset selection from a large number of training instances has been a successful approach toward efficient and cost-effective machine learning. However, models trained on a smaller subset may show poor generalization ability. In this paper, our goal is to design an algorithm for selecting a subset of the training data, so that the model can be trained quickly, without significantly sacrificing on accuracy. More specifically, we focus on data subset selection for $L_2$ regularized regression problems and provide a novel problem formulation which seeks to minimize the training loss with respect to both the trainable parameters and the subset of training data, subject to error bounds on the validation set. We tackle this problem using several technical innovations. First, we represent this problem with simplified constraints using the dual of the original training problem and show that the objective of this new representation is a monotone and $\alpha$-submodular function, for a wide variety of modeling choices. Such properties lead us to develop SELCON, an efficient majorization-minimization algorithm for data subset selection, that admits an approximation guarantee even when the training provides an imperfect estimate of the trained model. Finally, our experiments on several datasets show that SELCON trades off accuracy and efficiency more effectively than the current state-of-the-art.

Details

ECAI Conference 2020 Conference Paper

Robust Submodular Minimization with Applications to Cooperative Modeling

Rishabh K. Iyer

Robust Optimization is becoming increasingly important in machine learning applications. This paper studies the problem of robust submodular minimization subject to combinatorial constraints. Constrained Submodular Minimization arises in several applications such as co-operative cuts in image segmentation, co-operative matchings in image correspondence etc. Many of these models are defined over clusterings of data points (for example pixels in images), and it is important for these models to be robust to perturbations and uncertainty in the data. While several existing papers have studied robust submodular maximization, ours is the first work to study the minimization version under a broad range of combinatorial constraints including cardinality, knapsack, matroid as well as graph based constraints such as cuts, paths, matchings and trees. In each case, we provide scalable approximation algorithms and also study hardness bounds. Finally, we empirically demonstrate the utility of our algorithms on synthetic and real world datasets.

Details

ICML Conference 2016 Conference Paper

Algorithms for Optimizing the Ratio of Submodular Functions

Wenruo Bai
Rishabh K. Iyer
Kai Wei
Jeff A. Bilmes

We investigate a new optimization problem involving minimizing the Ratio of Submodular (RS) functions. We argue that this problem occurs naturally in several real world applications. We then show the connection between this problem and several related problems, including minimizing the difference of submodular functions, and to submodular optimization subject to submodular constraints. We show RS that optimization can be solved within bounded approximation factors. We also provide a hardness bound and show that our tightest algorithm matches the lower bound up to a \log factor. Finally, we empirically demonstrate the performance and good scalability properties of our algorithms.

Details

ICML Conference 2015 Conference Paper

Submodularity in Data Subset Selection and Active Learning

Kai Wei
Rishabh K. Iyer
Jeff A. Bilmes

We study the problem of selecting a subset of big data to train a classifier while incurring minimal performance loss. We show the connection of submodularity to the data likelihood functions for Naive Bayes (NB) and Nearest Neighbor (NN) classifiers, and formulate the data subset selection problems for these classifiers as constrained submodular maximization. Furthermore, we apply this framework to active learning and propose a novel scheme filtering active submodular selection (FASS), where we combine the uncertainty sampling method with a submodular data subset selection framework. We extensively evaluate the proposed framework on text categorization and handwritten digit recognition tasks with four different classifiers, including Deep Neural Network (DNN) based classifiers. Empirical results indicate that the proposed framework yields significant improvement over the state-of-the-art algorithms on all classifiers.

Details

ICML Conference 2014 Conference Paper

Fast Multi-stage Submodular Maximization

Kai Wei
Rishabh K. Iyer
Jeff A. Bilmes

We introduce a new multi-stage algorithmic framework for submodular maximization. We are motivated by extremely large scale machine learning problems, where both storing the whole data for function evaluation and running the standard accelerated greedy algorithm are prohibitive. We propose a multi-stage framework (called MultGreed), where at each stage we apply an approximate greedy procedure to maximize surrogate submodular functions. The surrogates serve as proxies for a target submodular function but require less memory and are easy to evaluate. We theoretically analyze the performance guarantee of the multi-stage framework, and give examples on how to design instances of MultGreed for a broad range of natural submodular functions. We show that MultGreed performs very close to the standard greedy algorithm, given appropriate surrogate functions, and argue how our framework can easily be integrated with distributive algorithms for optimization. We complement our theory by empirically evaluating on several real world problems, including data subset selection on millions of speech samples, where MultGreed yields at least a thousand times speedup and superior results over the state-of-the-art selection methods.

Details

UAI Conference 2014 Conference Paper

Monotone Closure of Relaxed Constraints in Submodular Optimization: Connections Between Minimization and Maximization

Rishabh K. Iyer
Stefanie Jegelka
Jeff A. Bilmes

It is becoming increasingly evident that many machine learning problems may be reduced to submodular optimization. Previous work addresses generic discrete approaches and specific relaxations. In this work, we take a generic view from a relaxation perspective. We show a relaxation formulation and simple rounding strategy that, based on the monotone closure of relaxed constraints, reveals analogies between minimization and maximization problems, and includes known results as special cases and extends to a wider range of settings. Our resulting approximation factors match the corresponding integrality gaps. For submodular maximization, a number of relaxation approaches have been proposed. A critical challenge for the practical applicability of these techniques, however, is the complexity of evaluating the multilinear extension. We show that this extension can be efficiently evaluated for a number of useful submodular functions, thus making these otherwise impractical algorithms viable for real-world machine learning problems.

Details

ICML Conference 2013 Conference Paper

Fast Semidifferential-based Submodular Function Optimization

Rishabh K. Iyer
Stefanie Jegelka
Jeff A. Bilmes

We present a practical and powerful new framework for both unconstrained and constrained submodular function optimization based on discrete semidifferentials (sub- and super-differentials). The resulting algorithms, which repeatedly compute and then efficiently optimize submodular semigradients, offer new and generalize many old methods for submodular optimization. Our approach, moreover, takes steps towards providing a unifying paradigm applicable to both submodular minimization and maximization, problems that historically have been treated quite distinctly. The practicality of our algorithms is important since interest in submodularity, owing to its natural and wide applicability, has recently been in ascendance within machine learning. We analyze theoretical properties of our algorithms for minimization and maximization, and show that many state-of-the-art maximization algorithms are special cases. Lastly, we complement our theoretical analyses with supporting empirical experiments.

Details

UAI Conference 2013 Conference Paper

The Lovasz-Bregman Divergence and connections to rank aggregation, clustering, and web ranking

Rishabh K. Iyer
Jeff A. Bilmes

We extend the recently introduced theory of Lovász Bregman (LB) divergences [19] in several ways. We show that they represent a distortion between a “score” and an “ordering”, thus providing a new view of rank aggregation and order based clustering with interesting connections to web ranking. We show how the LB divergences have a number of properties akin to many permutation based metrics, and in fact have as special cases forms very similar to the Kendall-τ metric. We also show how the LB divergences subsume a number of commonly used ranking measures in information retrieval, like NDCG [22] and AUC [35]. Unlike the traditional permutation based metrics, however, the LB divergence naturally captures a notion of “confidence” in the orderings, thus providing a new representation to applications involving aggregating scores as opposed to just orderings. We show how a number of recently used web ranking models are forms of Lovász Bregman rank aggregation and also observe that a natural form of Mallow’s model using the LB divergence has been used as conditional ranking models for the “Learning to Rank” problem.

Details

UAI Conference 2012 Conference Paper

Algorithms for Approximate Minimization of the Difference Between Submodular Functions, with Applications

Rishabh K. Iyer
Jeff A. Bilmes

We extend the work of Narasimhan and Bilmes [30] for minimizing set functions representable as a difference between submodular functions. Similar to [30], our new algorithms are guaranteed to monotonically reduce the objective function at every step. We empirically and theoretically show that the per-iteration cost of our algorithms is much less than [30], and our algorithms can be used to efficiently minimize a difference between submodular functions under various combinatorial constraints, a problem not previously addressed. We provide computational bounds and a hardness result on the multiplicative inapproximability of minimizing the difference between submodular functions. We show, however, that it is possible to give worst-case additive bounds by providing a polynomial time computable lower-bound on the minima. Finally we show how a number of machine learning problems can be modeled as minimizing the difference between submodular functions. We experimentally show the validity of our algorithms by testing them on the problem of feature selection with submodular cost features.

Details