Copertina

Control, Transport and Sampling: Towards Better Loss Design

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Jiang, Qijia, Nabergoj, David
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Computation
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Machine-Learned Sampling of Conditioned Path Measures
di: Jiang, Qijia, et al.
Pubblicazione: (2025)

Reducing normalizing flow complexity for MCMC preconditioning
di: Nabergoj, David, et al.
Pubblicazione: (2025)

Designing Algorithms for Entropic Optimal Transport from an Optimisation Perspective
di: Srinivasan, Vishwak, et al.
Pubblicazione: (2025)

Empirical evaluation of normalizing flows in Markov Chain Monte Carlo
di: Nabergoj, David, et al.
Pubblicazione: (2024)

A General Approach to Visualizing Uncertainty in Statistical Graphics
di: Petek, Bernarda, et al.
Pubblicazione: (2025)

Towards Better Multi-head Attention via Channel-wise Sample Permutation
di: Yuan, Shen, et al.
Pubblicazione: (2024)

Rejection Sampling IMLE: Designing Priors for Better Few-Shot Image Synthesis
di: Vashist, Chirag, et al.
Pubblicazione: (2024)

Is the Frequency Principle always valid?
di: Zhai, Qijia
Pubblicazione: (2025)

ConFu: Contemplate the Future for Better Speculative Sampling
di: Qin, Zongyue, et al.
Pubblicazione: (2026)

Sample Smart, Not Hard: Correctness-First Decoding for Better Reasoning in LLMs
di: Li, Xueyan, et al.
Pubblicazione: (2025)

Towards Better Understanding Attribution Methods
di: Rao, Sukrut, et al.
Pubblicazione: (2022)

Better than Random: Reliable NLG Human Evaluation with Constrained Active Sampling
di: Ruan, Jie, et al.
Pubblicazione: (2024)

Are Sparse Neural Networks Better Hard Sample Learners?
di: Xiao, Qiao, et al.
Pubblicazione: (2024)

Posterior Sampling with Denoising Oracles via Tilted Transport
di: Bruna, Joan, et al.
Pubblicazione: (2024)

Towards Better Open-Ended Text Generation: A Multicriteria Evaluation Framework
di: Arias, Esteban Garces, et al.
Pubblicazione: (2024)

Towards Better Understanding of In-Context Learning Ability from In-Context Uncertainty Quantification
di: Liu, Shang, et al.
Pubblicazione: (2024)

Towards a Better Evaluation of Out-of-Domain Generalization
di: Hwang, Duhun, et al.
Pubblicazione: (2024)

Generative Data Refinement: Just Ask for Better Data
di: Jiang, Minqi, et al.
Pubblicazione: (2025)

$\mathbb{X}$-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs
di: Sobal, Vlad, et al.
Pubblicazione: (2024)

Unified Interpretation of Smoothing Methods for Negative Sampling Loss Functions in Knowledge Graph Embedding
di: Feng, Xincan, et al.
Pubblicazione: (2024)

Learning Paths for Dynamic Measure Transport: A Control Perspective
di: Maurais, Aimee, et al.
Pubblicazione: (2025)

Triplets Better Than Pairs: Towards Stable and Effective Self-Play Fine-Tuning for LLMs
di: Wang, Yibo, et al.
Pubblicazione: (2026)

Split-Flows: Measure Transport and Information Loss Across Molecular Resolutions
di: Hummerich, Sander, et al.
Pubblicazione: (2025)

CARD: Towards Conditional Design of Multi-agent Topological Structures
di: Wu, Tongtong, et al.
Pubblicazione: (2026)

Nested Slice Sampling: Vectorized Nested Sampling for GPU-Accelerated Inference
di: Yallup, David, et al.
Pubblicazione: (2026)

Subset Selection for Stratified Sampling in Online Controlled Experiments
di: Momozu, Haru, et al.
Pubblicazione: (2025)

Discounted Adaptive Online Learning: Towards Better Regularization
di: Zhang, Zhiyu, et al.
Pubblicazione: (2024)

ABC: Achieving Better Control of Multimodal Embeddings using VLMs
di: Schneider, Benjamin, et al.
Pubblicazione: (2025)

Sample Efficient Omniprediction and Downstream Swap Regret for Non-Linear Losses
di: Lu, Jiuyao, et al.
Pubblicazione: (2025)

MM-SpuBench: Towards Better Understanding of Spurious Biases in Multimodal LLMs
di: Ye, Wenqian, et al.
Pubblicazione: (2024)

Towards Better Sample Efficiency in Multi-Agent Reinforcement Learning via Exploration
di: Baghi, Amir, et al.
Pubblicazione: (2025)

Optimal Transport-Induced Samples against Out-of-Distribution Overconfidence
di: Tang, Keke, et al.
Pubblicazione: (2026)

Detecting OOD Samples via Optimal Transport Scoring Function
di: Gao, Heng, et al.
Pubblicazione: (2025)

Demystifying Diffusion Objectives: Reweighted Losses are Better Variational Bounds
di: Shi, Jiaxin, et al.
Pubblicazione: (2025)

Towards Meta-Pruning via Optimal Transport
di: Theus, Alexander, et al.
Pubblicazione: (2024)

Towards Robust Few-Shot Text Classification Using Transformer Architectures and Dual Loss Strategies
di: Han, Xu, et al.
Pubblicazione: (2025)

Annealing Flow Generative Models Towards Sampling High-Dimensional and Multi-Modal Distributions
di: Wu, Dongze, et al.
Pubblicazione: (2024)

Loss-to-Loss Prediction: Scaling Laws for All Datasets
di: Brandfonbrener, David, et al.
Pubblicazione: (2024)

How PC-based Methods Err: Towards Better Reporting of Assumption Violations and Small Sample Errors
di: Faltenbacher, Sofia, et al.
Pubblicazione: (2025)

Energy-Based Preference Model Offers Better Offline Alignment than the Bradley-Terry Preference Model
di: Hong, Yuzhong, et al.
Pubblicazione: (2024)