header photo


Publications



Working Papers

  • Sobolev Descent (Submitted to ICML 2018).
  • Revisiting Matching Pursuit (Submitted to ICML 2018).
  • Improved Bounds for Distribution Regression. 
  • Variance Reduction in Stochastic Optimization (Submitted to ICML 2018).
  • A Differentially Private Kernel Two-Sample Test (Submitted to UAI 2018).

Papers / Manuscripts (* Denotes Equal Work)
  • Youssef Mroueh, Chun-Liang Li*, Tom Sercu*, Anant Raj* and Yu Cheng.
    "Sobolev GAN" [pdf]    (Contribution in Theory)
    in 6th International Conference on Learning Representations (ICLR) , Canada, 2018 

  • Sebastian Stich, Anant Raj and Martin Jaggi.
    "Safe Adaptive Importance Sampling" [pdf]    (Spotlight  Presentation, in top 3% papers)
    in Advances in Neural Information System Conference (NIPS) 31, USA, 2017 

  • Sebastian Stich, Anant Raj and Martin Jaggi.
    "Approximate Steepest Coordinate Descent" [pdf]
    in 34th International Conference on Machine Learning (ICML), AU, 2017

  • Anant Raj, Abhishek Kumar, Youssef Mroueh, P Thomas Fletcher and Bernhard Schölkopf.
    "Local Group Invariant Representations via Orbit Embeddings" [pdf]
    in 20th International Conference on Artificial Intelligence and Statistics (AISTATS), USA, 2017

  • Anant Raj, Jakob Olbrich, Bernd Gärtner, Bernhard Schölkopf and Martin Jaggi.
    "Screening Rules for Convex Problems" [pdf]
    arxiv-Preprint, 2016
     ( A shorter version of the paper was also presented at Optimization for Machine Learning        Workshop at NIPS 2016)

  • Ayush Mittal, Anant Raj, V. Namboodiri and T. Tuytelaars.
    "Unsupervised Domain Adaptation in the Wild: Dealing with Asymmetric Label Sets" [pdf]
    arxiv-Preprint, 2016

  • Anant Raj, V. Namboodiri and T. Tuytelaars.
    "Subspace Alignement based Domain Adaptation for RCNN detector" [pdf]
    in 26th British Machine Vision Conference (BMVC), UK, 2015

  • Anant Raj, V. Namboodiri and T. Tuytelaars.
    "Mind the Gap: Subspace based Hierarchical Domain Adaptation" [pdf]
    in Transfer and Multi-task learning Workshop in Advances in Neural Information System Conference (NIPS) 27, Canada, 2014

  • B. Dai, B. Xie, N. He, Y. Liang, Anant Raj, M. Balcan and L. Song.
    "Scalable Kernel Methods via Doubly Stochastic Gradients" [pdf]
    in Advances in Neural Information System Conference (NIPS) 27, Canada, 2014

  • D. Arya, Anant Raj, and R. Hegde.
    "Significance of Variable Height Bandwidth Group Delay Filter in the Spectral Reconstruction of Speech" [pdf]
    in the 14th Annual Conference of the International Speech Communication Association (INTERSPEECH), France, 2013