ℓ₂-Boosting exhibits benign overfitting with logarithmic excess variance decay Θ(σ²/log(p/n)) under isotropic noise due to ℓ₁ bias, and a subdifferential early stopping rule recovers minimax-optimal ℓ₁ rates.
International conference on machine learning , pages=
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 8roles
background 1polarities
background 1representative citing papers
Proposes pointwise Riemannian Dimension from feature eigenvalues to derive tighter, representation-aware generalization bounds for deep networks in the nonlinear regime.
A generative transfer framework using iterative path-wise tilting integrated with conditional flow matching recovers target entropic optimal transport couplings from reference samples, achieving O(δ) convergence in Wasserstein-1 distance.
ACT blocks enable neural operators to learn adaptive coordinate systems via differentiable sampling, yielding consistent accuracy gains on PDE benchmarks by reducing spatial misalignment and operator complexity.
Standard preference learning induces spurious feature reliance via mean bias and correlation leakage, creating irreducible distribution shift vulnerabilities that tie training mitigates without degrading causal learning.
PnP-Corrector decouples physics simulation from error correction via a plug-and-play agent, cutting error by 29% in 300-day global ocean-atmosphere forecasts.
S4 models exhibit stable time-continuity unlike sensitive S6 models, with task continuity predicting performance and enabling temporal subsampling for better efficiency.
citing papers explorer
-
When Does $\ell_2$-Boosting Overfit Benignly? High-Dimensional Risk Asymptotics and the $\ell_1$ Implicit Bias
ℓ₂-Boosting exhibits benign overfitting with logarithmic excess variance decay Θ(σ²/log(p/n)) under isotropic noise due to ℓ₁ bias, and a subdifferential early stopping rule recovers minimax-optimal ℓ₁ rates.
-
Pointwise Generalization in Deep Neural Networks
Proposes pointwise Riemannian Dimension from feature eigenvalues to derive tighter, representation-aware generalization bounds for deep networks in the nonlinear regime.
-
Generative Transfer for Entropic Optimal Transport with Unknown Costs
A generative transfer framework using iterative path-wise tilting integrated with conditional flow matching recovers target entropic optimal transport couplings from reference samples, achieving O(δ) convergence in Wasserstein-1 distance.
-
Adaptive Coordinate Transforms for Neural Operators
ACT blocks enable neural operators to learn adaptive coordinate systems via differentiable sampling, yielding consistent accuracy gains on PDE benchmarks by reducing spatial misalignment and operator complexity.
-
Spurious Correlation Learning in Preference Optimization: Mechanisms, Consequences, and Mitigation via Tie Training
Standard preference learning induces spurious feature reliance via mean bias and correlation leakage, creating irreducible distribution shift vulnerabilities that tie training mitigates without degrading causal learning.
-
PnP-Corrector: A Universal Correction Framework for Coupled Spatiotemporal Forecasting
PnP-Corrector decouples physics simulation from error correction via a plug-and-play agent, cutting error by 29% in 300-day global ocean-atmosphere forecasts.
-
Continuity Laws for Sequential Models
S4 models exhibit stable time-continuity unlike sensitive S6 models, with task continuity predicting performance and enabling temporal subsampling for better efficiency.
- FLUIDSPLAT: Reconstructing Physical Fields from Sparse Sensors via Gaussian Primitives