Presents first online L2D algorithm for multiclass classification with bandit feedback and varying experts, achieving O((n+n_e)T^{2/3}) regret generally and O((n+n_e)√T) under low noise.
Title resolution pending
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
dataset 1
citation-polarity summary
years
2026 7verdicts
UNVERDICTED 7representative citing papers
TRACE creates valid conformal prediction sets for complex generative models by scoring outputs via averaged denoising or velocity errors along stochastic transport paths instead of likelihoods.
HORST uses non-commutative operator composition and a hyperbolic mirror map to combine stability from adaptive optimizers with L1 sparsity bias, outperforming AdamW across sparsity levels on vision and language tasks.
Low-resolution data improves high-resolution model performance when high-resolution samples are limited, via KL-divergence bounds and experiments on vision transformers and CNNs.
wAR-Tok adds a Wasserstein-gradient-flow prior-matching term to tokenizer training so that discrete tokens become easier for autoregressive priors to model, cutting AR loss and raising generation FID on CIFAR-10 and ImageNet while keeping reconstruction quality comparable.
Scaling pretrained representations improves label-free OOD detection on frozen backbones, causing performance gaps between global and local detectors to vanish across vision and language tasks.
LSAMD searches a multi-dataset super Ans-Net to extract frequently selected base blocks as learngenes that initialize variable-sized Des-Nets with performance comparable to full pretrain-finetune at lower storage and training cost.
citing papers explorer
-
Online Learning-to-Defer with Varying Experts
Presents first online L2D algorithm for multiclass classification with bandit feedback and varying experts, achieving O((n+n_e)T^{2/3}) regret generally and O((n+n_e)√T) under low noise.
-
TRACE: Transport Alignment Conformal Prediction via Diffusion and Flow Matching Models
TRACE creates valid conformal prediction sets for complex generative models by scoring outputs via averaged denoising or velocity errors along stochastic transport paths instead of likelihoods.
-
HORST: Composing Optimizer Geometries for Sparse Transformer Training
HORST uses non-commutative operator composition and a hyperbolic mirror map to combine stability from adaptive optimizers with L1 sparsity bias, outperforming AdamW across sparsity levels on vision and language tasks.
-
On What We Can Learn from Low-Resolution Data
Low-resolution data improves high-resolution model performance when high-resolution samples are limited, via KL-divergence bounds and experiments on vision transformers and CNNs.
-
Learning Discrete Autoregressive Priors with Wasserstein Gradient Flow
wAR-Tok adds a Wasserstein-gradient-flow prior-matching term to tokenizer training so that discrete tokens become easier for autoregressive priors to model, cutting AR loss and raising generation FID on CIFAR-10 and ImageNet while keeping reconstruction quality comparable.
-
Scaling Pretrained Representations Enables Label-Free Out-of-Distribution Detection Without Fine-Tuning
Scaling pretrained representations improves label-free OOD detection on frozen backbones, causing performance gaps between global and local detectors to vanish across vision and language tasks.
-
Learngene Search Across Multiple Datasets for Building Variable-Sized Models
LSAMD searches a multi-dataset super Ans-Net to extract frequently selected base blocks as learngenes that initialize variable-sized Des-Nets with performance comparable to full pretrain-finetune at lower storage and training cost.