Tatsunori Hashimoto

Postdoc, Stanford

thashim [AT] stanford.edu

Bio

I am currently a post-doc at Stanford working for John C. Duchi and Percy Liang on tradeoffs between the average and worst-case performance of machine learning models. Machine learning systems do well on their training domain, but often fail in dramatic and unexpected ways in the wild. I view these problems as coverage issues - systems can appear to do well even if they fail on rare examples (in prediction) or plagiarize from the training set (in generation). My work seeks to develop evaluations, representations, and training procedures to guarantee uniform, rather than just average performance of machine learning models.

Before this, I was a graduate student at MIT co-advised by Tommi Jaakkola and David Gifford, and a undergraduate student at Harvard in statistics and math advised by Edoardo Airoldi.

Publications

Most recent publications on Google Scholar.

Distributionally Robust Losses Against Mixture Covariate Shifts

John C Duchi, Tatsunori B Hashimoto, Hongseok Namkoong

Preprint

Paper

A Retrieve-and-Edit Framework for Predicting Structured Outputs

Tatsunori B Hashimoto, Kelvin Guu, Yonatan Oren, Percy Liang

Advances in Neural Information Processing Systems 31 (NeurIPS 2018, Oral)

Paper

Fairness Without Demographics in Repeated Loss Minimization

Tatsunori B Hashimoto, Megha Srivastava, Hongseok Namkoong, Percy Liang

Proceedings of the 35th International Conference on Machine Learning (ICML 2018, Best paper runner up)

Paper

Derivative free optimization via repeated classification

Tatsunori B Hashimoto, Steve Yadlowsky, John C Duchi

21st International Conference on Artificial Intelligence and Statistics (AISTATS 2018)

Paper

Unsupervised Transformation Learning via Convex Relaxations

Tatsunori B Hashimoto, Percy S Liang, John C Duchi

Advances in Neural Information Processing Systems 30 (NeurIPS 2017)

Paper

Continuous representations and models from random walk diffusion limits

Tatsunori B Hashimoto

PhD Thesis, MIT CSAIL, 2016

Paper

Word embeddings as metric recovery in semantic spaces

Tatsunori B Hashimoto, David Alvarez-Melis, Tommi S Jaakkola

Transactions of the Association for Computational Linguistics 4 (TACL, presented at ACL 2016)

Paper

Learning Population-Level Diffusions with Generative RNNs

Tatsunori B Hashimoto, David Gifford, Tommi Jaakkola

Proceedings of the 33rd International Conference on Machine Learning (ICML 2016)

Paper

From random walks to distances on unweighted graphs

Tatsunori B Hashimoto, Yi Sun, Tommi Jaakkola

Advances in Neural Information Processing Systems (NeurIPS 2015)

Paper

Metric recovery from directed unweighted graphs

Tatsunori B Hashimoto, Yi Sun, Tommi Jaakkola

Artificial Intelligence and Statistics (AISTATS 2015), (best poster at NeurIPS 2014 workshop on networks)

Paper

Unifying Human and Statistical Evaluation for Natural Language Generation

Tatsunori B Hashimoto*, Hugh Zhang*, Percy Liang

Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2019, To appear)

Paper

A Retrieve-and-Edit Framework for Predicting Structured Outputs

Tatsunori B Hashimoto, Kelvin Guu, Yonatan Oren, Percy Liang

Advances in Neural Information Processing Systems 31 (NeurIPS 2018, Oral)

Paper

Generating Sentences by Editing Prototypes

Kelvin Guu*, Tatsunori B Hashimoto*, Yonatan Oren, Percy Liang

Transactions of the Association of Computational Linguistics (TACL, presented at ACL 2018)

Paper

Continuous representations and models from random walk diffusion limits

Tatsunori B Hashimoto

PhD Thesis, MIT CSAIL, 2016

Paper

Word embeddings as metric recovery in semantic spaces

Tatsunori B Hashimoto, David Alvarez-Melis, Tommi S Jaakkola

Transactions of the Association for Computational Linguistics 4 (TACL, presented at ACL 2016)

Paper

Inferring Multidimensional Rates of Aging from Cross-Sectional Data

Emma Pierson*, Pang Wei Koh *, Tatsunori B Hashimoto *, Daphne Koller, Jure Lesokevic, Nicholas Eriksson, Percy Liang

22nd International Conference on Artificial Intelligence and Statistics (AISTATS 2019)

Continuous representations and models from random walk diffusion limits

Tatsunori B Hashimoto

PhD Thesis, MIT CSAIL, 2016

Paper

Learning Population-Level Diffusions with Generative RNNs

Tatsunori B Hashimoto, David Gifford, Tommi Jaakkola

Proceedings of the 33rd International Conference on Machine Learning (ICML 2016)

Paper

A synergistic DNA logic predicts genome-wide chromatin accessibility

Tatsunori B Hashimoto*, Richard I Sherwood*, Daniel D Kang*, Nisha Rajagopal, Amira A Barkal, Haoyang Zeng, Bart JM Emons, Sharanya Srinivasan, Tommi Jaakkola, David K Gifford

Genome research (2016)

Paper

Cas9 Functionally Opens Chromatin

Amira A Barkal, Sharanya Srinivasan, Tatsunori B Hashimoto, David K Gifford, Richard I Sherwood

PloS One (2016)

Paper

Cloning-free CRISPR

Mandana Arbab, Sharanya Srinivasan, Tatsunori B Hashimoto, Niels Geijsen, Richard I Sherwood

Stem cell reports (2015)

Paper

GERV: a statistical method for generative evaluation of regulatory variants for transcription factor binding

Haoyang Zeng, Tatsunori B Hashimoto, Daniel D Kang, David K Gifford

Bioinformatics (2015)

Paper

Long-term persistence and development of induced pancreatic beta cells generated by lineage conversion of acinar cells

Weida Li, Claudia Cavelti-Weder, Yinying Zhang, Kendell Clement, Scott Donovan, Gabriel Gonzalez, Jiang Zhu, Marianne Stemann, Ke Xu, Tatsunori B Hashimoto, Takatsugu Yamada, Mio Nakanishi, Yuemei Zhang, Samuel Zeng, David Gifford, Alexander Meissner, Gordon Weir, Qiao Zhou

Nature Biotechnology (2014)

Paper

Universal count correction for high-throughput sequencing

Tatsunori B Hashimoto, Matthew D Edwards, David K Gifford

PLoS computational biology (2014)

Paper

Discovery of directional and nondirectional pioneer transcription factors by modeling DNase profile magnitude and shape

Richard I Sherwood *, Tatsunori B Hashimoto *, Charles W O'donnell *, Sophia Lewis, Amira A Barkal, John Peter Van Hoff, Vivek Karun, Tommi Jaakkola, David K Gifford

Nature Biotechnology (2014)

Paper

Quantifying condition-dependent intracellular protein levels enables high-precision fitness estimates

Kerry A Geiler-Samerotte, Tatsunori B Hashimoto, Michael F Dion, Bogdan A Budnik, Edoardo M Airoldi, D Allan Drummond

PloS one (2013)

Paper

Lineage-based identification of cellular states and expression programs

Tatsunori B Hashimoto, Tommi Jaakkola, Richard Sherwood, Esteban O. Mazzoni, Hynek Wichterle, David Gifford

Bioinformatics (2012)

Paper

Finding drug discovery rules of thumb with bump hunting

Tatsunori B Hashimoto, Matthew Segall

Proceedings of the ACS (2010)

Paper

BFL: a node and edge betweenness based fast layout algorithm for large scale networks.

Tatsunori B Hashimoto, Masao Nagasaki, Kaname Kojima, Satoru Miyano

BMC bioinformatics (2009)

Paper

Resume

Acknowledgement

This website uses the website design and template by Martin Saveski

Tatsunori Hashimoto
thashim [AT] stanford.edu