Copertina

Multi-Teacher Ensemble Distillation: A Mathematical Framework for Probability-Domain Knowledge Aggregation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Flouro, Aaron R., Chadwick, Shawn P.
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning 68T05 I.2.6
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Adaptive Weighting in Knowledge Distillation: An Axiomatic Framework for Multi-Scale Teacher Ensemble Optimization
di: Flouro, Aaron R., et al.
Pubblicazione: (2026)

Sparse Knowledge Distillation: A Mathematical Framework for Probability-Domain Temperature Scaling and Multi-Stage Compression
di: Flouro, Aaron R., et al.
Pubblicazione: (2026)

Recursive Meta-Distillation: An Axiomatic Framework for Iterative Knowledge Refinement
di: Flouro, Aaron R., et al.
Pubblicazione: (2026)

Post-Training Probability Manifold Correction via Structured SVD Pruning and Self-Referential Distillation
di: Flouro, Aaron R., et al.
Pubblicazione: (2026)

Hallucinations Live in Variance
di: Flouro, Aaron R., et al.
Pubblicazione: (2026)

Contrastive MIM: A Contrastive Mutual Information Framework for Unified Generative and Discriminative Representation Learning
di: Livne, Micha
Pubblicazione: (2025)

Tracking Changing Probabilities via Dynamic Learners
di: Madani, Omid
Pubblicazione: (2024)

Multi-Scale Graph Learning for Anti-Sparse Downscaling
di: Fan, Yingda, et al.
Pubblicazione: (2025)

Territory Paint Wars: Diagnosing and Mitigating Failure Modes in Competitive Multi-Agent PPO
di: Singh, Diyansha
Pubblicazione: (2026)

Temporal Taskification in Streaming Continual Learning: A Source of Evaluation Instability
di: Filat, Nicolae, et al.
Pubblicazione: (2026)

Fine-Tuning Regimes Define Distinct Continual Learning Problems
di: Iordache, Paul-Tiberiu, et al.
Pubblicazione: (2026)

Adaptive Exploration for Latent-State Bandits
di: Jin, Jikai, et al.
Pubblicazione: (2026)

Nonlinear Data Integration via Kernel Methods for Data Collaboration Analysis
di: Suetake, Yamato, et al.
Pubblicazione: (2026)

Effects of Initialization Biases on Deep Neural Network Training Dynamics
di: Pellegrino, Nicholas, et al.
Pubblicazione: (2025)

Contrastive Mutual Information Learning: Toward Robust Representations without Positive-Pair Augmentations
di: Livne, Micha
Pubblicazione: (2025)

When Redundancy Matters: Machine Teaching of Representations
di: Ferri, Cèsar, et al.
Pubblicazione: (2024)

Data structure > labels? Unsupervised heuristics for SVM hyperparameter estimation
di: Cholewa, Michał, et al.
Pubblicazione: (2021)

Generative Pretrained Embedding and Hierarchical Irregular Time Series Representation for Daily Living Activity Recognition
di: Bouchabou, Damien, et al.
Pubblicazione: (2024)

Reinforcement Learning for Stock Transactions
di: Zhou, Ziyi, et al.
Pubblicazione: (2025)

Understanding the Limits of Deep Tabular Methods with Temporal Shift
di: Cai, Hao-Run, et al.
Pubblicazione: (2025)

RVI-SAC: Average Reward Off-Policy Deep Reinforcement Learning
di: Hisaki, Yukinari, et al.
Pubblicazione: (2024)

Grammar-based evolutionary approach for automated workflow composition with domain-specific operators and ensemble diversity
di: Barbudo, Rafael, et al.
Pubblicazione: (2024)

Feature-aware Modulation for Learning from Temporal Tabular Data
di: Cai, Hao-Run, et al.
Pubblicazione: (2025)

Hard Samples, Bad Labels: Robust Loss Functions That Know When to Back Off
di: Pellegrino, Nicholas, et al.
Pubblicazione: (2025)

Data-Driven Preference Sampling for Pareto Front Learning
di: Ye, Rongguang, et al.
Pubblicazione: (2024)

Adaptive Bernstein Change Detector for High-Dimensional Data Streams
di: Heyden, Marco, et al.
Pubblicazione: (2023)

Lost in Aggregation: On a Fundamental Expressivity Limit of Message-Passing Graph Neural Networks
di: Rosenbluth, Eran
Pubblicazione: (2026)

Human-Aligned Skill Discovery: Balancing Behaviour Exploration and Alignment
di: Hussonnois, Maxence, et al.
Pubblicazione: (2025)

Correction and Corruption: A Two-Rate View of Error Flow in LLM Protocols
di: Reitich, Fernando
Pubblicazione: (2026)

Distinguished In Uniform: Self Attention Vs. Virtual Nodes
di: Rosenbluth, Eran, et al.
Pubblicazione: (2024)

Step-E: A Differentiable Data Cleaning Framework for Robust Learning with Noisy Labels
di: Du, Wenzhang
Pubblicazione: (2025)

GoldenStart: Q-Guided Priors and Entropy Control for Distilling Flow Policies
di: Zhang, He, et al.
Pubblicazione: (2026)

Your Data, My Model: Learning Who Really Helps in Federated Learning
di: Abdurakhmanova, Shamsiiat, et al.
Pubblicazione: (2024)

Evolving machine learning workflows through interactive AutoML
di: Barbudo, Rafael, et al.
Pubblicazione: (2024)

An Improved Adaptive PID Optimizer with Enhanced Convergence and Stability for Deep Learning
di: Saini, Saurabh, et al.
Pubblicazione: (2026)

MAcPNN: Mutual Assisted Learning on Data Streams with Temporal Dependence
di: Giannini, Federico, et al.
Pubblicazione: (2026)

A General Framework for Clustering and Distribution Matching with Bandit Feedback
di: Yavas, Recep Can, et al.
Pubblicazione: (2024)

Structured Basis Function Networks: Loss-Centric Multi-Hypothesis Ensembles with Controllable Diversity
di: Dominguez, Alejandro Rodriguez, et al.
Pubblicazione: (2025)

Knowledge Distillation: Enhancing Neural Network Compression with Integrated Gradients
di: Hernandez, David E., et al.
Pubblicazione: (2025)

MACS: Multi-Agent Reinforcement Learning for Optimization of Crystal Structures
di: Zamaraeva, Elena, et al.
Pubblicazione: (2025)