Sirisha Rambhatla

selected publications

1. 

   ICLR

   🏆 Travel Award

   NOODL: Provable Online Dictionary Learning and Sparse Coding

   Rambhatla, S., Li, X., and Haupt, J.

   International Conference on Learning Representations (ICLR) 2019

   Abs Bib arXiv PDF Code Slides

   We consider the dictionary learning problem, where the aim is to model the givendata as a linear combination of a few columns of a matrix known as adictionary,where the sparse weights forming the linear combination are known ascoeffi-cients. Since the dictionary and coefficients, parameterizing the linear model areunknown, the corresponding optimization is inherently non-convex. This was amajor challenge until recently, when provable algorithms for dictionary learningwere proposed. Yet, these provide guarantees only on the recovery of the dic-tionary, without explicit recovery guarantees on the coefficients. Moreover, anyestimation error in the dictionary adversely impacts the ability to successfully lo-calize and estimate the coefficients. This potentially limits the utility of existingprovable dictionary learning methods in applications where coefficient recoveryis of interest. To this end, we develop NOODL: a simple Neurally plausible alter-nating Optimization-based Online Dictionary Learning algorithm, which recoversboththe dictionary and coefficientsexactlyat a geometric rate, when initializedappropriately. Our algorithm, NOODL, is also scalable and amenable for largescale distributed implementations in neural architectures, by which we mean thatit only involves simple linear and non-linear operations. Finally, we corroboratethese theoretical results via experimental evaluation of the proposed algorithmwith the current state-of-the-art techniques.

   @article{Rambhatla2019, abbr = {ICLR}, title = {{NOODL}: Provable Online Dictionary Learning and Sparse Coding}, author = {Rambhatla, S. and Li, X. and Haupt, J.}, journal = {International Conference on Learning Representations (ICLR)}, year = {2019}, url = {https://openreview.net/forum?id=HJeu43ActQ}, selected = {true}, arxiv = {1902.11261}, slides = {/posters/NOODL_poster_ICLR.pdf}, pdf = {https://openreview.net/pdf?id=HJeu43ActQ}, code = {https://github.com/srambhatla/NOODL}, img = {NOODL.png}, award = {Travel Award} }

2. 

   NeurIPS

   Provable Online CP/PARAFAC Decomposition of a Structured Tensor via Dictionary Learning

   Rambhatla, S., Li, X., and Haupt, J.

   Advances in Neural Information Processing Systems (NeurIPS) 2020

   Abs Bib arXiv PDF Code Slides

   We consider the problem of factorizing a structured 3-way tensor into itsconstituent Canonical Polyadic (CP) factors. This decomposition, whichcan be viewed as a generalization of singular value decomposition (SVD)for tensors, reveals how the tensor dimensions (features) interact with eachother. However, since the factors area prioriunknown, the correspondingoptimization problems are inherently non-convex. The existing guaranteedalgorithms which handle this non-convexity incur an irreducible error (bias),and only apply to cases where all factors have the same structure. To thisend, we develop a provable algorithm for online structured tensor factor-ization, wherein one of the factors obeys some incoherence conditions, andthe others are sparse. Specifically we show that, under some relatively mildconditions on initialization, rank, and sparsity, our algorithm recovers thefactorsexactly(up to scaling and permutation) at a linear rate. Comple-mentary to our theoretical results, our synthetic and real-world data eval-uations showcase superior performance compared to related techniques.

   @article{Rambhatla19Tensor, abbr = {NeurIPS}, title = {Provable Online {CP/PARAFAC} Decomposition of a Structured Tensor via Dictionary Learning }, author = {Rambhatla, S. and Li, X. and Haupt, J.}, journal = {Advances in Neural Information Processing Systems (NeurIPS)}, slides = {/posters/Poster_TensorNOODL.pdf}, img = {TensorNOODL.png}, url = {https://papers.nips.cc/paper/2020/hash/85b42dd8aae56e01379be5736db5b496-Abstract.html}, pdf = {https://papers.nips.cc/paper/2020/file/85b42dd8aae56e01379be5736db5b496-Paper.pdf}, arxiv = {2006.16442}, code = {https://github.com/srambhatla/TensorNOODL}, selected = {true}, year = {2020} }

3. 

   NeurIPS

   How does this interaction affect me? Interpretable attribution for feature interactions

   Tsang, M., Rambhatla, S., and Liu, Y.

   Advances in Neural Information Processing Systems (NeurIPS) 2020

   Abs Bib arXiv PDF Code

   Machine learning transparency calls for interpretable explanations of how inputs relate to predictions. Feature attribution is a way to analyze the impact of features on predictions. Feature interactions are the contextual dependence between features that jointly impact predictions. There are a number of methods that extract feature interactions in prediction models; however, the methods that assign attributions to interactions are either uninterpretable, model-specific, or non-axiomatic. We propose an interaction attribution and detection framework called Archipelago which addresses these problems and is also scalable in real-world settings. Our experiments on standard annotation labels indicate our approach provides significantly more interpretable explanations than comparable methods, which is important for analyzing the impact of interactions on predictions. We also provide accompanying visualizations of our approach that give new insights into deep neural networks.

   @article{tsang2020does, abbr = {NeurIPS}, title = {How does this interaction affect me? Interpretable attribution for feature interactions}, author = {Tsang, M. and Rambhatla, S. and Liu, Y.}, journal = {Advances in Neural Information Processing Systems (NeurIPS)}, arxiv = {2006.10965}, pdf = {https://proceedings.neurips.cc/paper/2020/file/443dec3062d0286986e21dc0631734c9-Paper.pdf}, url = {https://proceedings.neurips.cc/paper/2020/hash/443dec3062d0286986e21dc0631734c9-Abstract.html}, code = {https://github.com/mtsang/archipelago}, img = {archipelago.png}, selected = {true}, year = {2020} }

4. 

   ICML 2024

   Why do Variational Autoencoders Really Promote Disentanglement?

   Bhowal, P., Soni, A., and Rambhatla, S.

   International Conference on Machine Learning (ICML) 2024

   Bib PDF

   @article{Bhowal2024, abbr = {ICML 2024}, img = {VAE-ICML-2024.png}, title = {Why do Variational Autoencoders Really Promote Disentanglement?}, author = {Bhowal, P. and Soni, A. and Rambhatla, S.}, journal = {International Conference on Machine Learning (ICML)}, pdf = {https://openreview.net/pdf?id=Ao9UUaScAU}, url = {https://proceedings.mlr.press/v235/bhowal24a.html}, year = {2024}, selected = {true} }

5. 

   NeurIPS 2024

   Seeing Beyond the Crop: Using Language Priors for Out-of-Bounding Box Keypoint Prediction

   Balaji, B., Bright, J., Chen, Y., Rambhatla, S., Zelek, J. S., and Clausi, D. A.

   Advances in Neural Information Processing Systems (NeurIPS) 2024

   Bib PDF

   @article{Balaji2024b, abbr = {NeurIPS 2024}, img = {NeurIPS-Token-Clip-Pose_2.png}, title = {Seeing Beyond the Crop: Using Language Priors for Out-of-Bounding Box Keypoint Prediction}, author = {Balaji, B. and Bright, J. and Chen, Y. and Rambhatla, S. and Zelek, J. S. and Clausi, D. A.}, journal = {Advances in Neural Information Processing Systems (NeurIPS)}, pdf = {https://openreview.net/pdf?id=LGus3wXPxc}, url = {https://openreview.net/forum?id=LGus3wXPxc}, year = {2024}, selected = {true} }

6. 

   ICCV 2025

   LOCATEdit: Graph Laplacian Optimized Cross Attention for Localized Text-Guided Image Editing

   Soni, A., Soni, M., and Rambhatla, S.

   IEEE International Conference on Computer Vision (ICCV) 2025

   Bib PDF Code

   @article{Soni2025, abbr = {ICCV 2025}, img = {LOCATEdit.jpg}, title = {LOCATEdit: Graph Laplacian Optimized Cross Attention for Localized Text-Guided Image Editing}, author = {Soni, A. and Soni, M. and Rambhatla, S.}, journal = {IEEE International Conference on Computer Vision (ICCV)}, pdf = {https://arxiv.org/pdf/2503.21541}, url = {https://locatedit.github.io}, code = {https://github.com/criticalml-uw/LOCATEdit}, year = {2025}, selected = {true} }

7. 

   NeurIPS 2025

   SubTrack++ : Gradient Subspace Tracking for Scalable LLM Training

   Rajabi, S., Nonta, N., and Rambhatla, S.

   In Advances in Neural Information Processing Systems (NeurIPS) 2025

   Bib PDF

   @inproceedings{Rajabi2025, abbr = {NeurIPS 2025}, img = {SubTrack++.jpg}, title = {SubTrack++ : Gradient Subspace Tracking for Scalable LLM Training}, author = {Rajabi, S. and Nonta, N. and Rambhatla, S.}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, pdf = {https://arxiv.org/abs/2502.01586}, year = {2025}, selected = {true} }

8. 

   NeurIPS 2026

   Pixels to Tokens: Token Space Efficient Active Learning for Low-Budget Semantic Segmentation

   Cicek, U., Singh, M., Shang, Z., Kaai, K., Thomas, C., Vela, P. P. G., Wong, A., and Rambhatla, S.

   In Advances in Neural Information Processing Systems (NeurIPS) 2026

   Bib PDF

   @inproceedings{Cicek2026, abbr = {NeurIPS 2026}, img = {Pixels2Token.png}, title = {Pixels to Tokens: Token Space Efficient Active Learning for Low-Budget Semantic Segmentation}, author = {Cicek, U. and Singh, M. and Shang, Z. and Kaai, K. and Thomas, C. and Vela, P. P. G. and Wong, A. and Rambhatla, S.}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, pdf = {https://arxiv.org/abs/2610.20881}, year = {2026}, selected = {true} }