7 citations · 18 across the 24 of their papers we have counts for
6 papers · 1 filter
Symmetric Divergence and Normalized Similarity: A Unified Topological Framework for Representation Analysis
Yan Wang, Tianyang Hu
Topological Data Analysis (TDA) offers a principled, intrinsic lens for comparing neural representations. However, existing paired topological divergences (e.g., RTD) are limited b…
Transformers Are Born Biased: Structural Inductive Biases at Random Initialization and Their Practical Consequences
Siquan Li, Yao Tong, Haonan Wang +1
Transformers underpin modern large language models (LLMs) and are commonly assumed to be behaviorally unstructured at random initialization, with all meaningful preferences emergin…
Exact Count of Boundary Pieces of ReLU Classifiers: Towards the Proper Complexity Measure for Classification
Paweł Piwek, Adam Klukowski, Tianyang Hu
Classic learning theory suggests that proper regularization is the key to good generalization and robustness. In classification, current training schemes only target the complexity…
Random Smoothing Regularization in Kernel Gradient Descent Learning
Liang Ding, Tianyang Hu, Jiahang Jiang +3
Random smoothing data augmentation is a unique form of regularization that can prevent overfitting by introducing noise to the input data, encouraging the model to learn more gener…
Sharp Rate of Convergence for Deep Neural Network Classifiers under the Teacher-Student Setting
Tianyang Hu, Zuofeng Shang, Guang Cheng
Classifiers built with neural networks handle large-scale high dimensional data, such as facial images from computer vision, extremely well while traditional statistical methods of…
Stein Neural Sampler
Tianyang Hu, Zixiang Chen, Hanxi Sun +3
We propose two novel samplers to generate high-quality samples from a given (un-normalized) probability density. Motivated by the success of generative adversarial networks, we con…