User profiles for S. Sagawa
Shiori SagawaPhD Student, Stanford University Verified email at stanford.edu Cited by 7019 |
On the opportunities and risks of foundation models
AI is undergoing a paradigm shift with the rise of models (eg, BERT, DALL-E, GPT-3) that are
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …
Wilds: A benchmark of in-the-wild distribution shifts
… We assess a model’s ability to normalize batch effects while preserving biological signal
by evaluating how well it can classify images of treated cells in the out-of-distribution test set. …
by evaluating how well it can classify images of treated cells in the out-of-distribution test set. …
Just train twice: Improving group robustness without training group information
Standard training via empirical risk minimization (ERM) can produce models that achieve low
error on average but high error on minority groups, especially in the presence of spurious …
error on average but high error on minority groups, especially in the presence of spurious …
Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization
… Classically, we can control the generalization gap with regularization techniques that
constrain the model family’s capacity to fit the training data. In the modern overparameterized …
constrain the model family’s capacity to fit the training data. In the modern overparameterized …
Common interest, common good: Creating value through business and social sector partnerships
S Sagawa, E Segal - California management review, 2000 - journals.sagepub.com
Almost anywhere you look you can find evidence of stepped-up busi-ness-social sector
interaction. Alongside traditional giving-a local store collecting toys for the needy at Christmas, a …
interaction. Alongside traditional giving-a local store collecting toys for the needy at Christmas, a …
Accuracy on the line: on the strong correlation between out-of-distribution and in-distribution generalization
For machine learning systems to be reliable, we must understand their performance in
unseen, out-of-distribution environments. In this paper, we empirically show that out-of-distribution …
unseen, out-of-distribution environments. In this paper, we empirically show that out-of-distribution …
An investigation of why overparameterization exacerbates spurious correlations
S Sagawa, A Raghunathan… - … on Machine Learning, 2020 - proceedings.mlr.press
We study why overparameterization—increasing model size well beyond the point of zero
training error—can hurt test error on minority groups despite improving average test error …
training error—can hurt test error on minority groups despite improving average test error …
Openflamingo: An open-source framework for training large autoregressive vision-language models
… This limits the academic community’s ability to conduct research on autoregressive vision-language …
For ease of comparison to Flamingo, we calculate each OpenFlamingo model’s …
For ease of comparison to Flamingo, we calculate each OpenFlamingo model’s …
Orientation of erythrocytes in a strong static magnetic field
…, T Takeuchi, N Kawaguchi, S Sagawa, S Onishi… - 1993 - ashpublications.org
… This phenomenon is ascribable to paramagnetic anisotropy retained by the heme of hemoglobin
S that is polymerized in fiber by deoxygenation. This paper deals with the Orientation of …
S that is polymerized in fiber by deoxygenation. This paper deals with the Orientation of …
Extending the wilds benchmark for unsupervised adaptation
… Self-training methods “pseudo-label” unlabeled examples with the model’s own predictions
and then train on them as if they were labeled examples. These methods often also use …
and then train on them as if they were labeled examples. These methods often also use …