Albert Gu |

Email: albertgu [at] stanford (dot) edu

Office: Gates 424, 353 Serra Mall, Stanford, CA 94305

**Efficiently Modeling Long Sequences with Structured State Spaces**

Albert Gu, Karan Goel, Christopher Ré

[OpenReview] [arXiv]

**Combining Recurrent, Convolutional, and Continuous-time Models with Linear State Space Layers**

Albert Gu, Isys Johnson, Karan Goel, Khaled Saab, Tri Dao, Atri Rudra, Christopher Ré

In*NeurIPS: Proceedings of the 34th Neural Information Processing Systems Conference*2021.

[arXiv]

**HoroPCA: Hyperbolic Dimensionality Reduction via Horospherical Projections**

Ines Chami*, Albert Gu*, Dat Nguyen*, Christopher Ré

In*ICML: The 38th International Conference on Machine Learning*, 2021.

[Paper] [arXiv]

**Catformer: Designing Stable Transformers via Sensitivity Analysis**

Jared Quincy Davis*, Albert Gu*, Krzysztof Choromanski, Tri Dao, Christopher Ré, Chelsea Finn, Percy Liang

In*ICML: The 38th International Conference on Machine Learning*, 2021.

[Paper]

**Model Patching: Closing the Subgroup Performance Gap with Data Augmentation**

Karan Goel*, Albert Gu*, Yixuan Li, Christopher Ré

In*ICLR: 9th International Conference on Learning Representations*2021.

[arXiv] [Code] [Video] [Blog]

**HiPPO: Recurrent Memory with Optimal Polynomial Projections**

Albert Gu*, Tri Dao*, Stefano Ermon, Atri Rudra, Christopher Ré

In*NeurIPS: Proceedings of the 33st Neural Information Processing Systems Conference*2020. (**Spotlight**)

[arXiv] [Code]

**From Trees to Continuous Embeddings and Back: Hyperbolic Hierarchical Clustering**

Ines Chami, Albert Gu, Vaggos Chatziafratis, Christopher Ré

In*NeurIPS: Proceedings of the 33rd Neural Information Processing Systems Conference*2020.

[Paper] [arXiv]

**No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems**

Nimit Sohoni, Jared Dunnmon, Geoff Angus, Albert Gu, Christopher Ré

In*NeurIPS: Proceedings of the 33rd Neural Information Processing Systems Conference*2020.

[arXiv]

**Improving the Gating Mechanism of Recurrent Neural Networks**

Albert Gu, Caglar Gulcehre, Tom Le Paine, Matt Hoffman, Razvan Pascanu

In*ICML: The 37th International Conference on Machine Learning*2020.

[Paper] [arXiv]

**Sparse Recovery for Orthogonal Polynomial Transforms**

Anna Gilbert, Albert Gu, Christopher Ré, Atri Rudra, Mary Wootters

In*ICALP: International Colloquium on Automata, Languages, and Programming*2020.

[arXiv]

**Kaleidoscope: An Efficient, Learnable Representation For All Structured Linear Maps**

Tri Dao, Nimit Sohoni, Albert Gu, Matthew Eichhorn, Amit Blonder, Megan Leszczynski, Atri Rudra, Christopher Ré

In*ICLR: 8th International Conference on Learning Representations*2020. (**Spotlight**)

[Paper] [Code] [Blogpost] [Video] [Slides]

**Learning Fast Algorithms for Linear Transforms Using Butterfly Factorizations**

Tri Dao, Albert Gu, Matthew Eichhorn, Atri Rudra, Christopher Ré

In*ICML: The 36th International Conference on Machine Learning*2019. (**Full Oral Presentation**)

[Paper] [arXiv] [Code]

**A Kernel Theory of Modern Data Augmentation**

Tri Dao, Albert Gu, Alexander J. Ratner, Virginia Smith, Christopher De Sa, Christopher Ré

In*ICML: The 36th International Conference on Machine Learning*2019.

[Paper] [arXiv] [Code] [Poster] [Slides]

**Learning Mixed-Curvature Representations in Products of Model Spaces**

Albert Gu, Fred Sala, Beliz Gunel, Christopher Ré

In*ICLR: 7th International Conference on Learning Representations*2019.

[Paper]

**Learning Compressed Transforms with Low Displacement Rank**

Anna T. Thomas*, Albert Gu*, Tri Dao, Atri Rudra, Christopher Ré

In*NIPS: Proceedings of the 31st Neural Information Processing Systems Conference*2018.

[arXiv] [Code]

Preliminary version:**Learning Invariance with Compact Transforms**

In*ICLR: 6th International Conference on Learning Representations, Workshop track*2018.

[Abstract]

**Representation Tradeoffs for Hyperbolic Embeddings**

Frederic Sala, Christopher De Sa, Albert Gu, Christopher Ré

In*ICML: Thirty-fifth International Conference on Machine Learning*2018.

[Paper]

[arXiv] [Code] [Blog]

**A Two-Pronged Progress in Structured Dense Matrix Vector Multiplication**

Christopher De Sa, Albert Gu, Rohan Puttagunta, Christopher Ré, Atri Rudra

In*SODA: ACM-SIAM Symposium on Discrete Algorithms*2018.

[Paper]

[arXiv]

**Sprague-Grundy Values of the R-Wythoff Game**

Albert Gu

In Electr. J. Comb. 22(2):2015.

[Paper]

**The Power of Deferral: Maintaining a Constant-Competitive Steiner Tree Online**

Albert Gu, Anupam Gupta, Amit Kumar

In*STOC: Proceedings of the forty-fifth annual ACM Symposium on Theory of Computing*2013.

In*SIAM Journal on Computing, 45(1):2016*

[STOC] [SICOMP]

[arXiv]

Teaching assistant at Stanford University for:

Probabilistic Graphical Models (CS228), Winter 2020

Convex Optimization I (EE364A), Winter 2018

Teaching assistant at Carnegie Mellon University for:

Parallel and Sequential Data Structures and Algorithms (15-210), Fall 2013

Putnam Competition: 8th place, 2014; 10th place, 2011

International Olympiad in Informatics: Gold medal, 2011