Optimizer choice induces distinct connected regions in the loss landscape of two-layer ReLU networks, with AdamW and Muon sometimes separated by provable barriers.
International workshop on multiple classifier systems , pages=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Global Bradley-Terry rankings of LLMs are misleading due to structured heterogeneity in user preferences, and small (λ, ν)-portfolios recover coherent subpopulations that cover over 96% of votes with just five rankings.
A lightweight multilingual encoder system with joint training and adaptive ensemble achieves top-half rankings across datasets in SemEval-2026 dimensional aspect sentiment regression.
citing papers explorer
-
Optimizer-Induced Mode Connectivity: From AdamW to Muon
Optimizer choice induces distinct connected regions in the loss landscape of two-layer ReLU networks, with AdamW and Muon sometimes separated by provable barriers.
-
Why Global LLM Leaderboards Are Misleading: Small Portfolios for Heterogeneous Supervised ML
Global Bradley-Terry rankings of LLMs are misleading due to structured heterogeneity in user preferences, and small (λ, ν)-portfolios recover coherent subpopulations that cover over 96% of votes with just five rankings.
-
ICT-NLP at SemEval-2026 Task 3: Less Is More -- Multilingual Encoder with Joint Training and Adaptive Ensemble for Dimensional Aspect Sentiment Regression
A lightweight multilingual encoder system with joint training and adaptive ensemble achieves top-half rankings across datasets in SemEval-2026 dimensional aspect sentiment regression.