Publications

Working Papers

1. Long–Range First–passage Percolation on with General Weights.

2. Practical Stochastic Policy Gradient Analysis: Fast Convergence and Robust Rate.

3. On the Benefits of Weighted ERM in Sub-regions.

4. Training Multi-Index Neural Network using SGD.

5. Improved bound for Learning with Abstention.

Research Articles (* denotes Equal Contribution)

1. Efficient Sampling of Stochastic Differential Equations with Positive Semi-Definite Models
   Anant Raj, Umut Şimşekli, and Alessandro Rudi
   Advances in Neural Information Processing Systems (Neurips), 2023.

2. Uniform-in-Time Wasserstein Stability Bounds for (Noisy) Stochastic Gradient Descent
   Lingjiong Zhu, Mert Gürbüzbalaban Anant Raj and Umut Şimşekli
   Advances in Neural Information Processing Systems (Neurips), 2023.

3. Variational Principles for Mirror Descent and Mirror Langevin Dynamics
   Belinda Tzen, Anant Raj, Maxim Raginsky and Francis Bach
   IEEE Control System Letters and IEEE Conference on Decision and Control (CDC), 2023.

4. Utilising the CLT Structure in Stochastic Gradient based Sampling : Improved Analysis and Faster Algorithms
   Aniket Das, Dheeraj Nagaraj, and Anant Raj
   Conference on Learning Theory (COLT), 2023.

5. Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions
   Anant Raj*, Lingjiong Zhu*, Mert Gürbüzbalaban and Umut Şimşekli
   International Conference on Machine Learning (ICML), 2023.

6. Explicit Regularization in Overparametrized Models via Noise Injection
   Antonio Orvieto*, Anant Raj*, Hans Kersting* and Francis Bach
   International Conference on Artificial Intelligence and Statistics (AISTATS), 2023.

7. Algorithmic Stability of Heavy-Tailed Stochastic Gradient Descent on Least Squares
   Anant Raj, Melih Barsbey, Mert Gürbüzbalaban, Lingjiong Zhu and Umut Şimşekli
   International Conference on Algorithmic Learning Theory (ALT), 2023.

8. Causal Feature Selection via Orthogonal Search
   Ashkan Soleymani*, Anant Raj*, Stefan Bauer, Michel Besserve and Bernhard Schölkopf
   Transactions on Machine Learning Research (TMLR), 2022.

9. Convergence of Uncertainty Sampling for Active Learning
   Anant Raj and Francis Bach
   International Conference on Machine Learning (ICML), 2022.

10. Faster Rates, Adaptive Algorithms, and Finite-Time Bounds for Linear Composition Optimization and Gradient TD Learning
    Anant Raj, Pooria Joulani, András György and Csaba Szepesvári
    International Conference on Artificial Intelligence and Statistics (AISTATS), 2022.

11. Explicit Regularization of Stochastic Gradient Methods through Duality
    Anant Raj and Francis Bach
    International Conference on Artificial Intelligence and Statistics (AISTATS), 2021.

12. A Simpler Approach to Accelerated Optimization: Iterative Averaging Meets Optimism
    Pooria Joulani*, Anant Raj*, András György and Csaba Szepesvári
    International Conference on Machine Learning (ICML), 2020.

13. Non-stationary online regression
    Anant Raj, Pierre Gaillard and Christophe Saad
    arXiv Preprint arXiv:2011.06957, 2020.

14. Model-specific Data Subsampling with Influence Functions
    Anant Raj, Cameron Musco, Lester Mackey and Nicolo Fusi
    arXiv Preprint arXiv:2010.10218, 2020.

15. Importance Sampling via Local Sensitivity
    Anant Raj, Cameron Musco and Lester Mackey
    International Conference on Artificial Intelligence and Statistics (AISTATS), 2020.

16. Stochastic Stein Discrepancies
    Jackson Gorham, Anant Raj and Lester Mackey
    Advances in Neural Information Processing Systems (Neurips), 2020.

17. Dual Instrumental Variable Regression
    Krikamol Muandet, Arash Mehrjou, Si Kai Lee and Anant Raj
    Advances in Neural Information Processing Systems (Neurips), 2020.

18. A Differentially Private Kernel Two-Sample Test
    Anant Raj, Ho Chung Leon Law, Dino Sejdinovic and Mijung Park
    Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD), 2019.

19. Sobolev Descent
    Youssef Mroueh, Tom Sercu and Anant Raj
    International Conference on Artificial Intelligence and Statistics (AISTATS), 2019.

20. k-SVRG: Variance Reduction for Large Scale Optimization
    Anant Raj and Sebastian U. Stich
    arXiv Preprint arXiv:1805.00982, 2018.

21. On Matching Pursuit and Coordinate Descent
    Francesco Locatello*, Anant Raj*, Sai Praneeth Reddy, Gunnar Rätsch, Bernhard Schölkopf, Sebastian U Stich and Martin Jaggi
    International Conference on Machine Learning (ICML), 2018.

22. Sobolev GAN
    Youssef Mroueh, Chun-Liang Li*, Tom Sercu*, Anant Raj* and Yu Cheng
    International Conference on Learning Representations (ICLR), 2018.

23. Safe Adaptive Importance Sampling
    Sebastian U. Stich, Anant Raj and Martin Jaggi
    Advances in Neural Information Processing Systems (Neurips), 2017.

24. Approximate Steepest Coordinate Descent
    Sebastian U. Stich, Anant Raj and Martin Jaggi
    International Conference on Machine Learning (ICML), 2017.

25. Local Group Invariant Representations via Orbit Embeddings
    Anant Raj, Abhishek Kumar, Youssef Mroueh, P. Thomas Fletcher and Bernhard Schölkopf
    International Conference on Artificial Intelligence and Statistics (AISTATS), 2017.

26. Screening Rules for Convex Problems
    Anant Raj, Jakob Olbrich, Bernd Gärtner, Bernhard Schölkopf and Martin Jaggi
    Optimization for Machine Learning Workshop (OPT 2016), 2016.

27. Unsupervised Domain Adaptation in the Wild: Dealing with Asymmetric Label Sets
    Ayush Mittal, Anant Raj, Vinay P. Namboodiri and Tinne Tuytelaars
    arXiv Preprint arXiv:1603.08105, 2016.

28. Subspace Alignment Based Domain Adaptation for RCNN Detector
    Anant Raj, Vinay P. Namboodiri and Tinne Tuytelaars
    British Machine Vision Conference (BMVC), 2015.

29. Mind the Gap: Subspace based Hierarchical Domain Adaptation
    Anant Raj, Vinay P Namboodiri and Tinne Tuytelaars
    Second Workshop on Transfer and Multi-Task Learning: Theory meets Practice in Neurips 2014.

30. Scalable kernel methods via doubly stochastic gradients
    Bo Dai, Bo Xie, Niao He, Yingyu Liang, Anant Raj, Maria-Florina F Balcan and Le Song
    Advances in Neural Information Processing Systems (Neurips), 2014.

31. Significance of variable height-bandwidth group delay filters in the spectral reconstruction of speech
    Devanshu Arya, Anant Raj and Rajesh M Hegde
    INTERSPEECH, 2013.