357 citations · 1.3k across the 33 of their papers we have counts for
22 papers · 1 filter
Corruption-tolerant Algorithms for Generalized Linear Models
Bhaskar P Mukhoty, Debojyoti Dey, Purushottam Kar
This paper presents SVAM (Sequential Variance-Altered MLE), a unified framework for learning generalized linear models under adversarial label corruption in training data. SVAM ext…
DELFI: Deep Mixture Models for Long-term Air Quality Forecasting in the Delhi National Capital Region
Naishadh Parmar, Raunak Shah, Tushar Goswamy +5
The identification and control of human factors in climate change is a rapidly growing concern and robust, real-time air-quality monitoring and forecasting plays a critical role in…
NGAME: Negative Mining-aware Mini-batching for Extreme Classification
Kunal Dahiya, Nilesh Gupta, Deepak Saini +16
Extreme Classification (XC) seeks to tag data points with the most relevant subset of labels from an extremely large label set. Performing deep XC with dense, learnt representation…
IGLU: Efficient GCN Training via Lazy Updates
S Deepak Narayanan, Aditya Sinha, Prateek Jain +2
Training multi-layer Graph Convolution Networks (GCN) using standard SGD techniques scales poorly as each descent step ends up updating node embeddings for a large portion of the g…
AngularGrad: A New Optimization Technique for Angular Convergence of Convolutional Neural Networks
S. K. Roy, M. E. Paoletti, J. M. Haut +4
Convolutional neural networks (CNNs) are trained using stochastic gradient descent (SGD)-based optimizers. Recently, the adaptive moment estimation (Adam) optimizer has become very…
Globally-convergent Iteratively Reweighted Least Squares for Robust Regression Problems
Bhaskar Mukhoty, Govind Gopakumar, Prateek Jain +1
We provide the first global model recovery results for the IRLS (iteratively reweighted least squares) heuristic for robust regression problems. IRLS is known to offer excellent pe…