Google Scholar
DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents Kushagra Pandey, Avideep Mukherjee, Piyush Rai, Abhishek Kumar arXiv Preprint, 2022
Solving Inverse Problems with NerfGANs Giannis Daras, Wen-Sheng Chu, Abhishek Kumar, Dmitry Lagun, Alexandros G. Dimakis arXiv Preprint, 2021
Constrained Instance and Class Reweighting for Robust Learning under Label Noise Abhishek Kumar, Ehsan Amid arXiv Preprint, 2021
Implicit Rate-constrained Optimization of Non-decomposable Objectives Abhishek Kumar, Harikrishna Narasimhan, Andrew Cotter International Conference on Machine Learning (ICML), 2021
Retrieve in Style: Unsupervised Facial Feature Transfer and Retrieval Min Jin Chong, Wen-Sheng Chu, Abhishek Kumar, David Forsyth International Conference on Computer Vision (ICCV), 2021 (to appear)
Score-Based Generative Modeling through Stochastic Differential Equations Yang Song, Jascha Sohl-Dickstein, Diederik P. Kingma, Abhishek Kumar, Stefano Ermon, Ben Poole International Conference on Learning Representations (ICLR), 2021 (Outstanding paper award)
Generalized Adversarially Learned Inference Yatin Dandi, Homanga Bharadhwaj, Abhishek Kumar, Piyush Rai AAAI, 2021
A Scale Invariant Flatness Measure for Deep Network Minima Akshay Rangamani, Nam H. Nguyen, Abhishek Kumar, Dzung Phan, Sang H. Chin, Trac D. Tran IEEE International Conf. on Acoustics, Speech and Signal Processing (ICASSP), 2021
Risk score learning for COVID-19 contact tracing apps Kevin Murphy, Abhishek Kumar, Stelios Serghiou Machine Learning for Healthcare (MLHC), 2021
Few-Shot Adaptation of Generative Adversarial Networks Esther Robb, Wen-Sheng Chu, Abhishek Kumar, Jia-Bin Huang arXiv Preprint, 2020
On Implicit Regularization in β-VAEs Abhishek Kumar, Ben Poole International Conference on Machine Learning (ICML), 2020 A shorter version appeared as a talk in BDL Workshop at NeurIPS, 2019
Regularized Autoencoders via Relaxed Injective Probability Flow Abhishek Kumar, Ben Poole, Kevin Murphy Intl. Conf. on Artificial Intelligence and Statistics (AISTATS), 2020 A shorter version appeared as a spotlight talk in INNF workshop at ICML, 2019
Weakly Supervised Disentanglement with Guarantees Rui Shu, Yining Chen, Abhishek Kumar, Stefano Ermon, Ben Poole International Conference on Learning Representations (ICLR), 2020
SpotTune: Transfer Learning through Adaptive Fine-tuning Yunhui Guo, Honghui Shi, Abhishek Kumar, Kristen Grauman, Tajana Rosing, Rogerio Feris IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2019
Co-regularized Alignment for Unsupervised Domain Adaptation Abhishek Kumar, Prasanna Sattigeri, Kahini Wadhawan, Leonid Karlinsky, Rogerio Feris, Bill Freeman, Gregory Wornell Adv. in Neural Information Processing Systems (NIPS), 2018
∆-encoder: an effective sample synthesis method for few-shot object recognition Eli Schwartz, Leonid Karlinsky, Joseph Shtok, Sivan Harary, Mattias Marder, Abhishek Kumar, Rogerio Feris, Raja Giryes, Alex M. Bronstein Adv. in Neural Information Processing Systems (NIPS), 2018 (Spotlight)
The Riemannian Geometry of Deep Generative Models Hang Shao, Abhishek Kumar, Tom Fletcher 4th Intl. Workshop on Differential Geometry in Computer Vision and Machine Learning at CVPR, 2018 (Oral)
BlockDrop: Dynamic Inference Paths in Residual Networks Zuxuan Wu, Tushar Nagarajan, Abhishek Kumar, Steven Rennie, Larry Davis, Kristen Grauman, Rogerio Feris IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2018 (Spotlight)
Variational Inference of Disentangled Latent Concepts from Unlabeled Observations Abhishek Kumar, Prasanna Sattigeri, Avinash Balakrishnan International Conference on Learning Representations (ICLR), 2018 A shorter version appeared in NIPS 2017 Workshop on Learning Disentangled Representations: from Perception to Control (Spotlight)
Semi-supervised Learning with GANs: Manifold Invariance with Improved Inference Abhishek Kumar, Prasanna Sattigeri, Tom Fletcher Adv. in Neural Information Processing Systems (NIPS), 2017
SenGen: Sentence Generating Neural Variational Topic Model, Ramesh Nallapati, Igor Melnyk, Abhishek Kumar, Bowen Zhou ICML Workshop on Learning to Generate Natural Language, 2017
Local Group Invariant Representations via Orbit Embeddings Anant Raj, Abhishek Kumar, Youssef Mroueh, Tom Fletcher, Bernhard Schölkopf Intl. Conf. on Artificial Intelligence and Statistics (AISTATS), 2017
Fully-adaptive Feature Sharing in Multi-Task Networks with Applications in Person Attribute Classification Yongxi Lu, Abhishek Kumar, Shuangfei Zhai, Yu Cheng, Tara Javidi, Rogerio Feris IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2017 (Spotlight)
S3Pool: Pooling with Stochastic Spatial Sampling Shuangfei Zhai, Hui Wu, Abhishek Kumar, Yu Cheng, Yongxi Lu, Zhongfei Zhang, Rogerio Feris IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2017
Incorporating Relational Knowledge into Word Representations using Subspace Regularization Abhishek Kumar, Jun Araki Proc. of Association for Computational Linguistics (ACL), 2016 (Oral, short paper)
Large-scale Submodular Greedy Exemplar Selection with Structured Similarity Matrices Dmitry Malioutov, Abhishek Kumar, Ian E.H. Yen Uncertainty in Artificial Intelligence (UAI), 2016
Scalable Exemplar Clustering and Facility Location via Augmented Block Coordinate Descent with Column Generation Ian E.H. Yen, Dmitry Malioutov, Abhishek Kumar Intl. Conf. on Artificial Intelligence and Statistics (AISTATS), 2016
Exact and Heuristic Algorithms for Semi-Nonnegative Matrix Factorization Nicolas Gillis, Abhishek Kumar SIAM Journal on Matrix Analysis and Applications (SIMAX), 2015
Near-separable Non-negative Matrix Factorization with ℓ1- and Bregman Loss Functions Abhishek Kumar, Vikas Sindhwani SIAM International Conference on Data Mining (SDM), 2015 (Oral, invited to Best of SDM, 2015) (Slightly modified version appeared as an invited book chapter in Robust Low-Rank and Sparse Matrix Decomposition: Applications in Image and Video Processing)
Fast Conical Hull Algorithms for Near-separable Non-negative Matrix Factorization Abhishek Kumar, Vikas Sindhwani, Prabhanjan Kambadur International Conference on Machine Learning (ICML), 2013 (Full oral presentation)
Simultaneously Leveraging Output and Task Structures for Multiple-Output Regression Piyush Rai, Abhishek Kumar, Hal Daumé III Adv. in Neural Information Processing Systems (NIPS), 2012
A Binary Classification Framework for Two-Stage Multiple Kernel Learning [supplement] [code] Abhishek Kumar, Alexandru Niculescu-Mizil, Koray Kavukcuoglu, Hal Daumé III International Conference on Machine Learning (ICML), 2012 (Full oral presentation)
Learning Task Grouping and Overlap in Multi-task Learning Abhishek Kumar, Hal Daumé III International Conference on Machine Learning (ICML), 2012 (Full oral presentation)
Generalized Multiview Analysis: A Discriminative Latent Space Abhishek Sharma, Abhishek Kumar, Hal Daumé III, David W. Jacobs IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2012
Mixed-Effects Shape Models for Estimating Longitudinal Changes in Anatomy Manasi Datar, P. Muralidharan, Abhishek Kuamar, Sylvain Gouttard, Joseph Piven, Guido Gerig, Ross Whitaker, Tom Fletcher 2nd International MICCAI Workshop on Spatiotemporal Image Analysis for Longitudinal and Time-Series Image Data (STIA), 2012
Co-regularized Multiview Spectral Clustering [code] Abhishek Kumar, Piyush Rai, Hal Daumé III Adv. in Neural Information Processing Systems (NIPS), 2011
A Co-training Approach for Multiview Spectral Clustering [code] Abhishek Kumar, Hal Daumé III International Conference on Machine Learning (ICML), 2011
Co-regularization Based Semi-supervised Domain Adaptation [supplement] Hal Daumé III, Abhishek Kumar, Avishek Saha Adv. in Neural Information Processing Systems (NIPS), 2010
A Kernel Mean Matching Approach for Environment Mismatch Compensation in Speech Recognition Abhishek Kumar, John H. L. Hansen IEEE International Conf. on Acoustics, Speech and Signal Processing (ICASSP), 2010
Co-regularized Spectral Clustering with Multiple Kernels Abhishek Kumar, Piyush Rai, Hal Daumé III NIPS 2010: Workshop on New Directions in Multiple Kernel Learning
Frustratingly Easy Semi-supervised Domain Adaptation Hal Daumé III, Abhishek Kumar, Avishek Saha ACL Workshop on Domain Adaptation for Natural Language Processing (DANLP), 2010
Environment Mismatch Compensation using Average Eigenspace for Speech Recognition Abhishek Kumar, John H. L. Hansen Interspeech, 2008
Slides for CMSC726 (convex losses, regularizers, gradient descent) (10/04/11)