Search Results for author:
Found 11 papers, 5 papers with code
PureGen: Universal Data Purification for Train-Time Poison Defense via Generative Model Dynamics
Train-time data poisoning attacks threaten machine learning models by introducing adversarial examples during training, leading to misclassification.
PureEBM: Universal Poison Purification via Mid-Run Dynamics of Energy-Based Models
Data poisoning attacks pose a significant threat to the integrity of machine learning models by leading to misclassification of target distribution data by injecting adversarial examples during training.
Curvature-Informed SGD via General Purpose Lie-Group Preconditioners
We present a novel approach to accelerate stochastic gradient descent (SGD) by utilizing curvature information obtained from Hessian-vector products or finite differences of parameters and gradients, similar to the BFGS algorithm.
Towards Composable Distributions of Latent Space Augmentations
We propose a composable framework for latent space image augmentation that allows for easy combination of multiple augmentations.
Generating High Fidelity Synthetic Data via Coreset selection and Entropic Regularization
Generative models have the ability to synthesize data points drawn from the data distribution, however, not all generated samples are high quality.
Improving Levenberg-Marquardt Algorithm for Neural Networks
We explore the usage of the Levenberg-Marquardt (LM) algorithm for regression (non-linear least squares) and classification (generalized Gauss-Newton methods) tasks in neural networks.
Causal Structural Hypothesis Testing and Data Generation Models
We show that the variational version of the architecture, Causal Structural Variational Hypothesis Testing can improve performance in low SNR regimes.
Adaptive Second Order Coresets for Data-efficient Machine Learning
We propose AdaCore, a method that leverages the geometry of the data to extract subsets of the training examples for efficient machine learning.
De-Biasing Generative Models using Counterfactual Methods
Our proposed method combines a causal latent space VAE model with specific modification to emphasize causal fidelity, enabling finer control over the causal layer and the ability to learn a robust intervention framework.
Diverse Imitation Learning via Self-Organizing Generative Models
Imitation learning is the task of replicating expert policy from demonstrations, without access to a reward function.
Diverse Imitation Learning via Self-OrganizingGenerative Models
To address this problem, we introduce a novel generative model for behavior cloning, in a mode-separating manner.
