activity
20242026
collaborators

7 papers

cs.LG2026

Learning to Discover Iterative Spectral Algorithms

Zihang Liu, Oleg Balabanov, Yaoqing Yang +1

We introduce AutoSpec, a neural network framework for discovering iterative spectral algorithms for large-scale numerical linear algebra and numerical optimization. Our self-superv…

cs.LG2026

Unveiling Multi-regime Patterns in SciML: Distinct Failure Modes and Regime-specific Optimization

Yuxin Wang, Yuanzhe Hu, Xiaokun Zhong +7

Neural networks trained under different hyperparameter settings can fall into distinct training "regimes," with consistent behavior within regimes and qualitative differences acros…

cs.LG2026

Landscaper: Understanding Loss Landscapes Through Multi-Dimensional Topological Analysis

Jiaqing Chen, Nicholas Hadler, Tiankai Xie +8

Loss landscapes are a powerful tool for understanding neural network optimization and generalization, yet traditional low-dimensional analyses often miss complex topological featur…

cs.LG2025

Mitigating Memorization In Language Models

Mansi Sakarvadia, Aswathy Ajith, Arham Khan +6

Language models (LMs) can "memorize" information, i.e., encode training data in their weights in such a way that inference-time queries can lead to verbatim regurgitation of that d…

cs.LG2024

Visualizing Loss Functions as Topological Landscape Profiles

Caleb Geniesse, Jiaqing Chen, Tiankai Xie +7

In machine learning, a loss function measures the difference between model predictions and ground-truth (or target) values. For neural network models, visualizing how this loss cha…

cs.LG2024

Evaluating Loss Landscapes from a Topology Perspective

Tiankai Xie, Caleb Geniesse, Jiaqing Chen +5

Characterizing the loss of a neural network with respect to model parameters, i.e., the loss landscape, can provide valuable insights into properties of that model. Various methods…