Search Results for author:
Found 21 papers, 6 papers with code
Improving Generalization via Meta-Learning on Hard Samples
In particular, we show that using hard-to-classify instances in the validation set has both a theoretical connection to, and strong empirical evidence of generalization.
Rescuing referral failures during automated diagnosis of domain-shifted medical images
Here, we address a fundamental challenge with selective classification during automated diagnosis with domain-shifted medical images.
Using Early Readouts to Mediate Featural Bias in Distillation
Deep networks tend to learn spurious feature-label correlations in real-world supervised learning tasks.
STREAMLINE: Streaming Active Learning for Realistic Multi-Distributional Settings
However, learning unbiased models depends on building a dataset that is representative of a diverse range of realistic scenarios for a given task.
Overcoming Simplicity Bias in Deep Networks using a Feature Sieve
Simplicity bias is the concerning tendency of deep networks to over-depend on simple, weakly predictive features, to the exclusion of stronger, more complex features.
Edges to Shapes to Concepts: Adversarial Augmentation for Robust Vision
We show that our augmentations significantly improve classification accuracy and robustness measures on a range of datasets and neural architectures.
Interactive Concept Bottleneck Models
Concept bottleneck models (CBMs) are interpretable neural networks that first predict labels for human-interpretable concepts relevant to the prediction task, and then predict the final label based on the concept label predictions.
Selective classification using a robust meta-learning approach
Predictive uncertainty-a model's self awareness regarding its accuracy on an input-is key for both building robust models via training interventions and for test-time applications such as selective classification.
Instance-Conditional Timescales of Decay for Non-Stationary Learning
Second, we learn an auxiliary scorer model that recovers the appropriate mixture of timescales as a function of the instance itself.
Robustifying Deep Vision Models Through Shape Sensitization
We also obtain gains of up to 28% and 8. 5% on natural adversarial and out-of-distribution datasets like ImageNet-A (for ViT-B) and ImageNet-R (for ViT-S), respectively.
Sample-Efficient Personalization: Modeling User Parameters as Low Rank Plus Sparse Components
We then study the framework in the linear setting, where the problem reduces to that of estimating the sum of a rank-$r$ and a $k$-column sparse matrix using a small number of linear measurements.
Shaken, and Stirred: Long-Range Dependencies Enable Robust Outlier Detection with PixelCNN++
We also show that our solutions work well with other types of generative models (generative flows and variational autoencoders) and that their efficacy is governed by each model's reliance on local dependencies.
Matching options to tasks using Option-Indexed Hierarchical Reinforcement Learning
The options framework in Hierarchical Reinforcement Learning breaks down overall goals into a combination of options or simpler tasks and associated policies, allowing for abstraction in the action space.
FLOAT: Factorized Learning of Object Attributes for Improved Multi-object Multi-part Scene Parsing
Our framework involves independent dense prediction of object category and part attributes which increases scalability and reduces task complexity compared to the monolithic label space counterpart.
Adaptive Mixing of Auxiliary Losses in Supervised Learning
In several supervised learning scenarios, auxiliary losses are used in order to introduce additional information or constraints into the supervised learning objective.
GCR: Gradient Coreset Based Replay Buffer Selection For Continual Learning
To address this, replay-based CL approaches maintain and repeatedly retrain on a small buffer of data selected across encountered tasks.
Robust outlier detection by de-biasing VAE likelihoods
Likelihoods computed by deep generative models (DGMs) are a candidate metric for outlier detection with unlabeled data.
End-to-End Neuro-Symbolic Architecture for Image-to-Image Reasoning Tasks
A key limitation is that such neural-to-symbolic models can only be trained end-to-end for tasks where the output space is symbolic.
Model-agnostic Fits for Understanding Information Seeking Patterns in Humans
In decision making tasks under uncertainty, humans display characteristic biases in seeking, integrating, and acting upon information relevant to the task.
Strategic Impatience in Go/NoGo versus Forced-Choice Decision-Making
We postulate that this ``impatience'' to go is a strategic adjustment in response to the implicit asymmetry in the cost structure of GNG: the NoGo response requires waiting until the response deadline, while a Go response immediately terminates the current trial.
A rational decision making framework for inhibitory control
Intelligent agents are often faced with the need to choose actions with uncertain consequences, and to modify those actions according to ongoing sensory processing and changing task demands.
