conftrace_

Soon Hoe Lim

7 papers · 2021–2025 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🗺️ Taxonomy Completionist (13)

Venues

AISTATS (2) ICLR (2) NeurIPS (2) JMLR (1)

Top co-authors

Michael W. Mahoney (4) N. Benjamin Erichson (4) Winnie Xu (2) Francisco Utrera (2) Benjamin Erichson (1) Michael Mahoney (1) Ziang Cao (1) Umut Simsekli (1) Liam Hodgkinson (1) Annan Yu (1)

Research topics

Deep Learning (7) Machine Learning (6) Architectures (5) Optimization & Theory · Machine Learning (4) Application Areas (2) Techniques (2) Learning Types (1) Optimization & Theory · Deep Learning (1)

Keywords

implicit regularization (3) model robustness (2) stochastic differential equation (2) sequential data (2) recurrent neural network (2) data augmentation (2) heavy-tailed distribution (1) decision boundary (1) noise injection (1) continuous-time model (1) long-range dependency (1) convex combination (1) sobolev norm (1) gated recurrent unit (1) long-term dependency (1) kernel methods (1) transfer function (1) neural network (1) delay differential equation (1) frequency bia (1)

Papers

Gated Recurrent Neural Networks with Weighted Time-Delay Feedback AISTATS 2025 Tuning Frequency Bias of State Space Models ICLR 2025 NoisyMix: Boosting Model Robustness to Common Corruptions AISTATS 2024 Chaotic Regularization and Heavy-Tailed Limits for Deterministic Gradient Descent NeurIPS 2022 Noisy Feature Mixup ICLR 2022 Noisy Recurrent Neural Networks NeurIPS 2021 Understanding Recurrent Neural Networks Using Nonequilibrium Response Theory JMLR 2021