Cover Image

Panprediction: Optimal Predictions for Any Downstream Task and Loss

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Balakrishnan, Sivaraman, Haghtalab, Nika, Hsu, Daniel, Lee, Brian, Zhao, Eric
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

On-Demand Sampling: Learning Optimally from Multiple Distributions
by: Haghtalab, Nika, et al.
Published: (2022)

From Style to Facts: Mapping the Boundaries of Knowledge Injection with Finetuning
by: Zhao, Eric, et al.
Published: (2025)

Learning With Multi-Group Guarantees For Clusterable Subpopulations
by: Dai, Jessica, et al.
Published: (2024)

On Surjectivity of Neural Networks: Can you elicit any behavior from your model?
by: Jiang, Haozhe, et al.
Published: (2025)

Diffusion Language Models are Provably Optimal Parallel Samplers
by: Jiang, Haozhe, et al.
Published: (2025)

Algorithmic Content Selection and the Impact of User Disengagement
by: Calvano, Emilio, et al.
Published: (2024)

ShakyPrepend: A Multi-Group Learner with Improved Sample Complexity
by: Zhang, Lujing, et al.
Published: (2026)

Truthfulness of Calibration Measures
by: Haghtalab, Nika, et al.
Published: (2024)

Stability Bounds for Smooth Optimal Transport Maps and their Statistical Implications
by: Balakrishnan, Sivaraman, et al.
Published: (2025)

Sample-Adaptivity Tradeoff in On-Demand Sampling
by: Haghtalab, Nika, et al.
Published: (2025)

Distortion of AI Alignment: Does Preference Optimization Optimize for Preferences?
by: Gölz, Paul, et al.
Published: (2025)

Delegating Data Collection in Decentralized Machine Learning
by: Ananthakrishnan, Nivasini, et al.
Published: (2023)

Statistical Inference for Optimal Transport Maps: Recent Advances and Perspectives
by: Balakrishnan, Sivaraman, et al.
Published: (2025)

Is Knowledge Power? On the (Im)possibility of Learning from Strategic Interactions
by: Ananthakrishnan, Nivasini, et al.
Published: (2024)

Plugin Estimation of Smooth Optimal Transport Maps
by: Manole, Tudor, et al.
Published: (2021)

Can Probabilistic Feedback Drive User Impacts in Online Platforms?
by: Dai, Jessica, et al.
Published: (2024)

Smooth Nash Equilibria: Algorithms and Complexity
by: Daskalakis, Constantinos, et al.
Published: (2023)

Learning in Stackelberg Games with Non-myopic Agents
by: Haghtalab, Nika, et al.
Published: (2022)

Improved Bayes Risk Can Yield Reduced Social Welfare Under Competition
by: Jagadeesan, Meena, et al.
Published: (2023)

Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation
by: Halawi, Danny, et al.
Published: (2024)

Any2Graph: Deep End-To-End Supervised Graph Prediction With An Optimal Transport Loss
by: Krzakala, Paul, et al.
Published: (2024)

ECG Latent Feature Extraction with Autoencoders for Downstream Prediction Tasks
by: Harvey, Christopher, et al.
Published: (2025)

Fairness-Optimized Synthetic EHR Generation for Arbitrary Downstream Predictive Tasks
by: Tarek, Mirza Farhan Bin, et al.
Published: (2024)

The Fundamental Limits of Structure-Agnostic Functional Estimation
by: Balakrishnan, Sivaraman, et al.
Published: (2023)

Comparison of Autoencoder Encodings for ECG Representation in Downstream Prediction Tasks
by: Harvey, Christopher J., et al.
Published: (2024)

On Robust Hypothesis Testing with respect to the Hellinger Distance
by: Modak, Eeshan, et al.
Published: (2025)

Smoke and Mirrors in Causal Downstream Tasks
by: Cadei, Riccardo, et al.
Published: (2024)

Semi-Supervised U-statistics
by: Kim, Ilmun, et al.
Published: (2024)

Subliminal Effects in Your Data: A General Mechanism via Log-Linearity
by: Aden-Ali, Ishaq, et al.
Published: (2026)

Mixing Configurations for Downstream Prediction
by: Wang, Juntang, et al.
Published: (2025)

AnyLoss: Transforming Classification Metrics into Loss Functions
by: Han, Doheon, et al.
Published: (2024)

Dataset Representativeness and Downstream Task Fairness
by: Borza, Victor, et al.
Published: (2024)

Symbolic Representation for Any-to-Any Generative Tasks
by: Chen, Jiaqi, et al.
Published: (2025)

Handling Missing Data in Downstream Tasks With Distribution-Preserving Guarantees
by: Bordoloi, Rahul, et al.
Published: (2025)

Aligning the Evaluation of Probabilistic Predictions with Downstream Value
by: Shahroudi, Novin, et al.
Published: (2025)

Double Cross-fit Doubly Robust Estimators: Beyond Series Regression
by: McClean, Alec, et al.
Published: (2024)

Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima
by: Chen, Huanran, et al.
Published: (2026)

Attacking Attention of Foundation Models Disrupts Downstream Tasks
by: Silva, Hondamunige Prasanna, et al.
Published: (2025)

Towards a Unified Representation Evaluation Framework Beyond Downstream Tasks
by: Plachouras, Christos, et al.
Published: (2025)

Pretraining Induces a Reusable Spectral Basis for Downstream Task Adaptation
by: Yu, Junjie, et al.
Published: (2026)