An Information-Geometric Distance on the Space of Tasks
Fuente:
arXiv
Guardado en:
| Autores principales: | Gao, Yansong, Chaudhari, Pratik |
|---|---|
| Formato: | Preprint |
| Publicado: |
2020
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
An Effective Gram Matrix Characterizes Generalization in Deep Networks
por: Yang, Rubing, et al.
Publicado: (2025)
por: Yang, Rubing, et al.
Publicado: (2025)
Model Zoo: A Growing "Brain" That Learns Continually
por: Ramesh, Rahul, et al.
Publicado: (2021)
por: Ramesh, Rahul, et al.
Publicado: (2021)
Budgeting Counterfactual for Offline RL
por: Liu, Yao, et al.
Publicado: (2023)
por: Liu, Yao, et al.
Publicado: (2023)
Learning Capacity: A Measure of the Effective Dimensionality of a Model
por: Chen, Daiwei, et al.
Publicado: (2023)
por: Chen, Daiwei, et al.
Publicado: (2023)
A Confidence Interval for the $\ell_2$ Expected Calibration Error
por: Sun, Yan, et al.
Publicado: (2024)
por: Sun, Yan, et al.
Publicado: (2024)
How does Chain of Thought decompose complex tasks?
por: Nadgir, Amrut, et al.
Publicado: (2026)
por: Nadgir, Amrut, et al.
Publicado: (2026)
Fast Feature Field ($\text{F}^3$): A Predictive Representation of Events
por: Das, Richeek, et al.
Publicado: (2025)
por: Das, Richeek, et al.
Publicado: (2025)
Language Modeling with Learned Meta-Tokens
por: Shah, Alok N., et al.
Publicado: (2025)
por: Shah, Alok N., et al.
Publicado: (2025)
Distillation of Discrete Diffusion by Exact Conditional Distribution Matching
por: Gao, Yansong, et al.
Publicado: (2025)
por: Gao, Yansong, et al.
Publicado: (2025)
ReLU Networks as Random Functions: Their Distribution in Probability Space
por: Chaudhari, Shreyas, et al.
Publicado: (2025)
por: Chaudhari, Shreyas, et al.
Publicado: (2025)
Heat Death of Generative Models in Closed-Loop Learning
por: Marchi, Matteo, et al.
Publicado: (2024)
por: Marchi, Matteo, et al.
Publicado: (2024)
Many Perception Tasks are Highly Redundant Functions of their Input Data
por: Ramesh, Rahul, et al.
Publicado: (2024)
por: Ramesh, Rahul, et al.
Publicado: (2024)
Deep Implicit Optimization enables Robust Learnable Features for Deformable Image Registration
por: Jena, Rohit, et al.
Publicado: (2024)
por: Jena, Rohit, et al.
Publicado: (2024)
Geometric SSM: LTI State Space Models for Selective Tasks
por: Casti, Umberto, et al.
Publicado: (2025)
por: Casti, Umberto, et al.
Publicado: (2025)
Adapting Machine Learning Diagnostic Models to New Populations Using a Small Amount of Data: Results from Clinical Neuroscience
por: Wang, Rongguang, et al.
Publicado: (2023)
por: Wang, Rongguang, et al.
Publicado: (2023)
Time-Varying Propensity Score to Bridge the Gap between the Past and Present
por: Fakoor, Rasool, et al.
Publicado: (2022)
por: Fakoor, Rasool, et al.
Publicado: (2022)
Prospective Learning in Retrospect
por: Bai, Yuxin, et al.
Publicado: (2025)
por: Bai, Yuxin, et al.
Publicado: (2025)
Stateful KV Cache Management for LLMs: Balancing Space, Time, Accuracy, and Positional Fidelity
por: Poudel, Pratik
Publicado: (2025)
por: Poudel, Pratik
Publicado: (2025)
Magnitude Distance: A Geometric Measure of Dataset Similarity
por: Torkamani, Sahel, et al.
Publicado: (2026)
por: Torkamani, Sahel, et al.
Publicado: (2026)
FLAME: Adaptive Mixture-of-Experts for Continual Multimodal Multi-Task Learning
por: Han, Xing, et al.
Publicado: (2026)
por: Han, Xing, et al.
Publicado: (2026)
Bridging the Training-Inference Gap in LLMs by Leveraging Self-Generated Tokens
por: Cen, Zhepeng, et al.
Publicado: (2024)
por: Cen, Zhepeng, et al.
Publicado: (2024)
Geometric Reasoning in the Embedding Space
por: Hůla, Jan, et al.
Publicado: (2025)
por: Hůla, Jan, et al.
Publicado: (2025)
LOFT: Low-Rank Orthogonal Fine-Tuning via Task-Aware Support Selection
por: Zhao, Lanxin, et al.
Publicado: (2026)
por: Zhao, Lanxin, et al.
Publicado: (2026)
Is Distance Matrix Enough for Geometric Deep Learning?
por: Li, Zian, et al.
Publicado: (2023)
por: Li, Zian, et al.
Publicado: (2023)
Meanings and Feelings of Large Language Models: Observability of Latent States in Generative AI
por: Liu, Tian Yu, et al.
Publicado: (2024)
por: Liu, Tian Yu, et al.
Publicado: (2024)
Prospective Learning: Learning for a Dynamic Future
por: De Silva, Ashwin, et al.
Publicado: (2024)
por: De Silva, Ashwin, et al.
Publicado: (2024)
Tree-Sliced Wasserstein Distance: A Geometric Perspective
por: Tran, Viet-Hoang, et al.
Publicado: (2024)
por: Tran, Viet-Hoang, et al.
Publicado: (2024)
Task Addition in Multi-Task Learning by Geometrical Alignment
por: Yim, Soorin, et al.
Publicado: (2024)
por: Yim, Soorin, et al.
Publicado: (2024)
Adversarial Multi-dueling Bandits
por: Gajane, Pratik
Publicado: (2024)
por: Gajane, Pratik
Publicado: (2024)
Calibrated Similarity for Reliable Geometric Analysis of Embedding Spaces
por: Tacheny, Nicolas
Publicado: (2026)
por: Tacheny, Nicolas
Publicado: (2026)
Spatio-temporal DeepKriging in PyTorch: A Supplementary Application to Precipitation Data for Interpolation and Probabilistic Forecasting
por: Nag, Pratik
Publicado: (2025)
por: Nag, Pratik
Publicado: (2025)
A Set-to-Set Distance Measure in Hyperbolic Space
por: Li, Pengxiang, et al.
Publicado: (2025)
por: Li, Pengxiang, et al.
Publicado: (2025)
Bootstrapping Task Spaces for Self-Improvement
por: Jiang, Minqi, et al.
Publicado: (2025)
por: Jiang, Minqi, et al.
Publicado: (2025)
Neural Lattice Reduction: A Self-Supervised Geometric Deep Learning Approach
por: Marchetti, Giovanni Luca, et al.
Publicado: (2023)
por: Marchetti, Giovanni Luca, et al.
Publicado: (2023)
Enhancing selectivity using Wasserstein distance based reweighing
por: Worah, Pratik
Publicado: (2024)
por: Worah, Pratik
Publicado: (2024)
A Goemans-Williamson type algorithm for identifying subcohorts in clinical trials
por: Worah, Pratik
Publicado: (2025)
por: Worah, Pratik
Publicado: (2025)
An Information-Geometric Approach to Artificial Curiosity
por: Nedergaard, Alexander, et al.
Publicado: (2025)
por: Nedergaard, Alexander, et al.
Publicado: (2025)
Sparse Crosscoders for diffing MoEs and Dense models
por: Chaudhari, Marmik, et al.
Publicado: (2026)
por: Chaudhari, Marmik, et al.
Publicado: (2026)
Towards Calibrated Losses for Adversarial Robust Reject Option Classification
por: Shah, Vrund, et al.
Publicado: (2024)
por: Shah, Vrund, et al.
Publicado: (2024)
What is the Right Notion of Distance between Predict-then-Optimize Tasks?
por: Rodriguez-Diaz, Paula, et al.
Publicado: (2024)
por: Rodriguez-Diaz, Paula, et al.
Publicado: (2024)
Ejemplares similares
-
An Effective Gram Matrix Characterizes Generalization in Deep Networks
por: Yang, Rubing, et al.
Publicado: (2025) -
Model Zoo: A Growing "Brain" That Learns Continually
por: Ramesh, Rahul, et al.
Publicado: (2021) -
Budgeting Counterfactual for Offline RL
por: Liu, Yao, et al.
Publicado: (2023) -
Learning Capacity: A Measure of the Effective Dimensionality of a Model
por: Chen, Daiwei, et al.
Publicado: (2023) -
A Confidence Interval for the $\ell_2$ Expected Calibration Error
por: Sun, Yan, et al.
Publicado: (2024)