Search Results for author:
Found 12 papers, 3 papers with code
Robust NAS under adversarial training: benchmark, theory, and beyond
Recent developments in neural architecture search (NAS) emphasize the significance of considering robust architectures against malicious data.
Benign Overfitting in Deep Neural Networks under Lazy Training
This paper focuses on over-parameterized deep neural networks (DNNs) with ReLU activation functions and proves that when the data distribution is well-separated, DNNs can achieve Bayes-optimal test error for classification while obtaining (nearly) zero-training error under the lazy training regime.
Regularization of polynomial networks for image recognition
We introduce a class of PNs, which are able to reach the performance of ResNet across a range of six benchmarks.
Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study
Neural tangent kernel (NTK) is a powerful tool to analyze training dynamics of neural networks and their generalization bounds.
Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization)
In particular, when initialized with LeCun initialization, depth helps robustness with the lazy training regime.
Generalization Properties of NAS under Activation and Skip Connection Search
To this end, we derive the lower (and upper) bounds of the minimum eigenvalue of the Neural Tangent Kernel (NTK) under the (in)finite-width regime using a certain search space including mixed activation functions, fully connected, and residual neural networks.
Sound and Complete Verification of Polynomial Networks
Polynomial Networks (PNs) have demonstrated promising performance on face and image recognition recently.
Adversarial Audio Synthesis with Complex-valued Polynomial Networks
Our models can encourage the systematic design of other efficient architectures on the complex field.
Controlling the Complexity and Lipschitz Constant improves polynomial nets
While the class of Polynomial Nets demonstrates comparable performance to neural networks (NN), it currently has neither theoretical generalization characterization nor robustness guarantees.
Cluster-guided Image Synthesis with Unconditional Models
The results highlight the ability of our approach to condition image generation on attributes like gender, pose and hair style on faces, as well as a variety of features on different object classes.
Augmenting Deep Classifiers with Polynomial Neural Networks
The efficacy of the proposed models is evaluated on standard image and audio classification benchmarks.
Ranked #2 on
Audio Classification
on Speech Commands
CoPE: Conditional image generation using Polynomial Expansions
We exhibit how CoPE can be trivially augmented to accept an arbitrary number of input variables.
