Search Results for author:
Found 8 papers, 4 papers with code
Evidence of Meaning in Language Models Trained on Programs
We present evidence that language models can learn meaning despite being trained only to perform next token prediction on text, specifically a corpus of programs.
Neural Architecture Search using Property Guided Synthesis
To enable this approach, we also propose a novel efficient synthesis procedure, which accepts a set of promising program properties, and returns a satisfying neural architecture.
Defending Against Backdoor Attacks Using Ensembles of Weak Learners
We propose an iterative training procedure for removing poisoned data from the training set.
Efficient Regularization for Adversarially Robustness Deep ReLU Networks
Crucially, our models are simultaneously robust against multiple state-of-the-art adversaries, suggesting that the robustness generalizes well to \textit{unseen} adversaries.
Incompatibility Clustering as a Defense Against Backdoor Poisoning Attacks
We propose a novel clustering mechanism based on an incompatibility property between subsets of data that emerges during model training.
Context-Agnostic Learning Using Synthetic Data
We propose a novel setting for learning, where the input domain is the image of a map defined on the product of two sets, one of which completely determines the labels.
Towards Context-Agnostic Learning Using Synthetic Data
We propose a novel setting for learning, where the input domain is the image of a map defined on the product of two sets, one of which completely determines the labels.
Manifold Regularization for Locally Stable Deep Neural Networks
We apply concepts from manifold regularization to develop new regularization techniques for training locally stable deep neural networks.
