Search Results for author:
Found 9 papers, 7 papers with code
A Data-Based Perspective on Transfer Learning
It is commonly believed that in transfer learning including more pre-training data translates into better performance.
When does Bias Transfer in Transfer Learning?
Using transfer learning to adapt a pre-trained "source model" to a downstream "target task" can dramatically increase performance with seemingly no downside.
Distilling Model Failures as Directions in Latent Space
Existing methods for isolating hard subpopulations and spurious correlations in datasets often require human intervention.
Missingness Bias in Model Debugging
Missingness, or the absence of features from an input, is a concept fundamental to many model debugging tools.
Combining Diverse Feature Priors
To improve model generalization, model designers often restrict the features that their models use, either implicitly or explicitly.
Certified Patch Robustness via Smoothed Vision Transformers
Certified patch defenses can guarantee robustness of an image classifier to arbitrary changes within a bounded contiguous region.
A Mechanism for Producing Aligned Latent Spaces with Autoencoders
Aligned latent spaces, where meaningful semantic shifts in the input space correspond to a translation in the embedding space, play an important role in the success of downstream tasks such as unsupervised clustering and data imputation.
Learning to Speak and Act in a Fantasy Text Adventure Game
We analyze the ingredients necessary for successful grounding in this setting, and how each of these factors relate to agents that can talk and act successfully.
MASA: Motif-Aware State Assignment in Noisy Time Series Data
Such data can be interpreted as a sequence of states, where each state represents a prototype of system behavior.
