Search Results for author:
Found 11 papers, 6 papers with code
No Spurious Local Minima in a Two Hidden Unit ReLU Network
Deep learning models can be efficiently optimized via stochastic gradient descent, but there is little theoretical evidence to support this.
Guarantees for Tuning the Step Size using a Learning-to-Learn Approach
Solving this problem using a learning-to-learn approach -- using meta-gradient descent on a meta-objective based on the trajectory that the optimizer generates -- was recently shown to be effective.
Secure Data Sharing With Flow Model
In the classical multi-party computation setting, multiple parties jointly compute a function without revealing their own input data.
Dissecting Hessian: Understanding Common Structure of Hessian in Neural Networks
We can analyze the properties of these smaller matrices and prove the structure of top eigenspace random 2-layer networks.
Beyond Lazy Training for Over-parameterized Tensor Decomposition
We show that in a lazy training regime (similar to the NTK regime for neural networks) one needs at least $m = \Omega(d^{l-1})$, while a variant of gradient descent can find an approximate tensor when $m = O^*(r^{2. 5l}\log d)$.
Towards Understanding the Data Dependency of Mixup-style Training
Despite seeing very few true data points during training, models trained using Mixup seem to still minimize the original empirical risk and exhibit better generalization and robustness on various tasks when compared to standard training.
Provably Learning Diverse Features in Multi-View Data with Midpoint Mixup
Mixup is a data augmentation technique that relies on training using random convex combinations of data points and their labels.
Hiding Data Helps: On the Benefits of Masking for Sparse Coding
Furthermore, drawing from the growing body of work on self-supervised learning, we propose a novel masking objective for which recovering the ground-truth dictionary is in fact optimal as the signal increases for a large class of data-generating processes.
BenchMD: A Benchmark for Unified Learning on Medical Images and Sensors
Finally, we evaluate performance on out-of-distribution data collected at different hospitals than the training data, representing naturally-occurring distribution shifts that frequently degrade the performance of medical AI models.
The Role of Linguistic Priors in Measuring Compositional Generalization of Vision-Language Models
Compositionality is a common property in many modalities including natural languages and images, but the compositional generalization of multi-modal models is not well-understood.
DF-DM: A foundational process model for multimodal data fusion in the artificial intelligence era
In the big data era, integrating diverse data modalities poses significant challenges, particularly in complex fields like healthcare.
