Paper designs a lossy compression method for lossless prediction.
problem Ensuring high performance on predictive tasks with minimal data.
method Characterizes bit-rate requirements for invariant transformations, designs unsupervised objectives for neural compressors.
result Achieves substantial rate savings on ImageNet compared to JPEG without compromising classification performance.
This study examines how the size and alignment of pretraining data affect the performance of large language models on downstream tasks.
problem Understanding how the size and alignment of pretraining data impact the performance of large language models on downstream tasks.
method Investigated the scaling behavior of large language models in a transfer learning setting, focusing on machine translation tasks.
result The size of the finetuning dataset and the distribution alignment between pretraining and downstream data significantly influence the scaling behavior of downstream performance.
TaskMet learns a metric to improve model performance on unseen tasks.
problem Deep models trained on one task may struggle on another task due to conflicting objectives.
method TaskMet learns a metric in the prediction space to balance task and prediction losses.
result TaskMet achieves better performance on downstream tasks without altering the prediction model.
Study improves healthcare time series imputation by considering structured missingness.
problem Structured missingness in clinical data impacts time series imputation models.
method Analysis of different masking strategies on imputation methods using PhysioNet Challenge 2012 dataset.
result Masking choices significantly affect imputation accuracy and clinical prediction.
New method optimizes treatment policies to avoid winner's curse.
problem Winner's curse in treatment policy optimization.
method Inference-aware policy optimization.
result Optimizes for both estimated performance and downstream evaluation.
Language models help text classification tasks by predicting next words.
problem Lack of theoretical understanding of why language models perform well on downstream tasks.
method Mathematical study of the connection between next word prediction and text classification, formalizing it and quantifying the benefit.
result Language models that are ε-optimal in cross-entropy learn features that can solve classification tasks with linear approximation.
Study shows uncertainty of deep learning models can be measured from their embeddings.
problem Uncertainty in contrastive learning models for critical applications.
method Estimating the distribution of training data in embedding space and accounting for local consistency.
result Uncertainty of an embedding vector correlates strongly with downstream accuracy.
Survey on uncertainty in GNNs for improved model reliability.
problem Inherent randomness and model training errors lead to unstable GNN predictions.
method Comprehensive overview of GNN uncertainty theory and methods.
result Integration of uncertainty in GNNs enhances model performance and reliability.
Pre-training improves model coverage, crucial for downstream performance.
problem Understanding why pre-training enhances model performance.
method Coverage principle, focusing on next-token prediction and model quality.
result Coverage generalizes faster than cross-entropy, improving downstream performance.
The paper explores how word embeddings affect the stability of downstream NLP models.
problem Small changes in training data can cause significant changes in model predictions.
method Empirical and theoretical analysis of embedding instability, including the introduction of eigenspace instability measure.
result Increasing embedding memory can reduce the disagreement in predictions by 5% to 37%.
New algorithm balances spatial data approximation and prediction accuracy.
problem Lack of methods considering spatial correlation and downstream modeling in dimension reduction.
method Formalizes approximation and modeling utility as metrics, proposes a balanced algorithm.
result Optimal trade-off between approximation accuracy and downstream modeling utility.
This work studies the impact of intra-/inter-class diversity on pre-training datasets and finds a balance for optimal performance.
problem The impact of intra-/inter-class diversity on supervised pre-training datasets and their effect on downstream tasks.
method Empirical study and theoretical analysis of the relationship between diversity types and downstream performance.
result The optimal class-to-sample ratio is invariant to the size of the pre-training dataset and can be predicted.
New method selects relevant dimensions for better prediction in mixtures.
problem Learning mixtures with limited components for prediction tasks.
method Prediction-focused modeling for mixtures.
result Improves prediction performance compared to non-focused models.
DKPS provides guarantees for synthetic data from Transformer models, improving downstream tasks.
problem Lack of labeled data for building performant AI models.
method Data Kernel Perspective Space (DKPS) for mathematical analysis of synthetic data quality.
result Concrete statistical guarantees for the quality of transformer model outputs.
New method predicts wind farm power and wakes using weather patterns.
problem Inefficient and computationally intensive wind energy resource assessment.
method Unsupervised clustering of ERA5 data on wind velocity, WRF simulations at cluster centers, and post-processing.
result Accurate long-term predictions of power and wakes with reduced computational time.
The Neural Testbed evaluates joint predictions of neural agents, revealing their limitations.
problem Evaluating the quality of joint predictions generated by neural agents.
method Developed an open-source benchmark (The Neural Testbed) to assess agents' marginal and joint predictions.
result Popular Bayesian deep learning agents perform poorly on joint predictions, even with accurate marginal predictions.
AI bias arises from human-defined goals, not algorithmic flaws.
problem AI bias due to human-defined goals in LLMs.
method Purpose-conditioned cognition and revealing downstream use of LLM outputs.
result AI bias can be reduced by purpose-aware prompting but not fully by regularization.
Paper defines and solves a problem in representation learning to ensure fairness with high confidence.
problem Learning fair representations with high confidence guarantees for all downstream tasks.
method Formally defines the problem, introduces FRG framework, proves high probability fairness, and demonstrates effectiveness empirically.
result FRG framework provides high-confidence guarantees for limiting unfairness across all downstream models and tasks.
Improved tabular models learn better from real-world data.
problem Tabular models perform poorly on real-world datasets when trained only on synthetic data.
method Continued pre-training on a curated set of real-world datasets.
result Real-TabPFN achieves superior predictive accuracy on 29 datasets.
Object-centric learning improves generalization and robustness in multi-object scenes.
problem Improving generalization and robustness in neural networks for scenes with multiple objects.
method Training state-of-the-art unsupervised models on multi-object datasets and evaluating segmentation metrics and downstream tasks.
result Object-centric representations are useful for downstream tasks and generally robust to most distribution shifts affecting objects, but less so for less structured shifts.
Proposes CAL to learn causal adjacency for better spatiotemporal prediction.
problem Suboptimal performance in spatiotemporal prediction due to out-of-distribution data.
method Causal Adjacency Learning (CAL) method to discover causal relations over graphs.
result Calculated causal adjacency matrix enhances prediction performance on out-of-distribution test data.
Contextual linear optimization shows naive plug-in methods can outperform direct optimization.
problem Optimizing decisions with side observations to reduce uncertainty.
method Using off-the-shelf machine learning methods to learn a predictive model and plug it in for optimization.
result The naive plug-in approach achieves faster regret convergence rates than direct optimization methods.
Lazy SPCA simplifies SPCA for large datasets with similar performance.
problem Efficiently reducing high-dimensional datasets for large-scale computations.
method Derives a simplified algorithm (Lazy SPCA) with reduced computational complexity.
result Lazy SPCA finds the same principal subspace as SPCA and maintains similar pairwise distances.
Paper shows distillation can maintain low model churn.
problem Maintaining low model churn in real-world systems.
method Equivalence between distillation and explicit churn constraints.
result Distillation significantly reduces model churn with minimal accuracy loss.
ExplaiNE offers explanations for NE-based link predictions.
problem Lack of transparency in NE methods for link prediction.
method Identifies counterfactual explanations for NE-based LP methods.
result Accuracy and scalability demonstrated for ExplaiNE.
Geospatial ML models need special evaluation methods due to their unique challenges.
problem Evaluating geospatial machine learning models is challenging due to their specific characteristics.
method Delineated unique challenges and proposed concrete takeaways for improving geospatial model evaluations.
result Concrete takeaways for improving evaluations of geospatial model performance.
Study shows scaling up models doesn't always improve downstream tasks.
problem Understanding why scaling up models doesn't always improve downstream performance.
method Systematic study of 4800 experiments on various models, analyzing performance on 20 downstream tasks.
result Performance on downstream tasks saturates as model size increases, revealing a nonlinear relationship.
PRAGMA models financial event sequences for various banking tasks.
problem Handling diverse financial data for multiple applications.
method Pre-training a Transformer model on a large banking event corpus with a self-supervised objective.
result PRAGMA achieves superior performance across multiple financial domains from raw event sequences.
DGC clusters data with side-information for better prediction.
problem Improving clustering strategies through better prediction performance.
method Deep Goal-Oriented Clustering (DGC) framework that clusters data using supervision and unsupervised modeling.
result Achieves prediction accuracies comparable to state-of-the-art, while learning congruent clustering strategies.
NGAT predicts long-term stock trends using graph attention networks.
problem Lack of effective corporate relationship graph comparison methods and model complexity in stock prediction.
method Developed a Node-level Graph Attention Network (NGAT) for corporate relationship graphs.
result Demonstrated the effectiveness of NGAT across two datasets.
Paper uses diffusion model to denoise financial time series data.
problem Low signal-to-noise ratio in financial time series data.
method Conditional diffusion model for progressive noise addition and removal.
result Denoised financial time series improve future return classification and trading performance.
This paper improves cross-domain learning using random forests for manifold alignment.
problem Improving cross-domain learning and feature integration.
method Semi-supervised manifold alignment using random forest proximities.
result Random forest proximities enhance downstream classification accuracy.
The paper predicts loss scaling across different datasets and compute scales.
problem Predicting loss scaling across different datasets and compute scales.
method Derive shifted power law relationships between train and test losses.
result Shifted power law relationships hold for various datasets and tasks, improving prediction accuracy.
CIT and CIF improve feature selection for downstream prediction.
problem Feature selection bias in machine learning models.
method Conditional inference trees and forests with Bonferroni correction.
result CIF ranks top 3 among 18 regression methods and top 4 among 17 classification methods.
Decision-calibrated prediction sets improve power system operations by reducing unnecessary costs.
problem Balancing operating costs and reliability in power systems with renewable uncertainty.
method Learn conditional prediction sets as sub-level sets of norm-based score functions, calibrate uncertainty sets based on reliability of downstream decisions.
result Decision-calibrated sets lead to more efficient operations with smaller uncertainty sets and lower costs compared to standard coverage-based calibration.
New approach optimizes decisions based on uncertainty in predictions.
problem Mismatch between prediction accuracy and decision loss in sequential design.
method Directional uncertainty-guided approach to sequential experimental design.
result Directional uncertainty-based design stops earlier and performs better.
Introduces lookahead counterfactual fairness to account for downstream effects of ML predictions.
problem Downstream effects of ML predictions on individuals not considered by counterfactual fairness.
method Introduces lookahead counterfactual fairness (LCF), a new fairness notion that considers future status. Proposes an algorithm based on theoretical conditions.
result Proposes an algorithm to achieve lookahead counterfactual fairness and validates it on synthetic and real data.
Proposes Decodable Information Bottleneck for optimal representation learning.
problem Finding optimal representations for supervised learning.
method Integrates information retention and compression with the desired predictive family.
result Optimal representations lead to better expected test performance and can be estimated with guarantees.
Proposes a new metric to quantify the difference between neural network representations based on downstream task performance.
problem The lack of a consistent metric to measure the difference between neural network representations.
method Introduced the Transferred Discrepancy (TD) metric, which evaluates the difference between representations based on their performance on downstream tasks.
result TD provides fine-grained information for various downstream tasks and can evaluate the effectiveness of different training strategies.
End-to-end approach for weak supervision improves downstream model performance.
problem Data-labeling bottleneck in machine learning applications.
method Directly learning the downstream model by maximizing its agreement with probabilistic labels generated from weak supervision sources.
result Improved performance over prior work in terms of downstream model performance and robustness.
Paper improves molecular property prediction using denoising autoencoders.
problem Limited data for molecular property prediction from 3D structures.
method Pre-training via denoising for learning molecular force fields.
result Achieves new state-of-the-art performance on QM9 dataset.
dboost optimizes prediction models for convex cone problems.
problem Optimizing prediction models for decision-making.
method Gradient boosting with implicit differentiation for convex quadratic cone programming.
result dboost reduces out-of-sample decision regret.
Theoretical analysis shows pretext-based self-supervised learning can be boosted by downstream data under certain conditions.
problem Theoretical analysis of pretext-based self-supervised learning and downstream data refinement.
method Theoretical analysis and experiments on synthetic and real-world datasets.
result Theoretical lower bounds and experiments show that downstream data refinement can boost or hurt performance depending on conditions.
Robust reinforcement learning agents generalize well to out-of-distribution settings using pretrained representations.
problem Achieving sample-efficient reinforcement learning agents that generalize to real-world settings.
method Trained 240 representations and 10,000 RL policies on a simulated robotic setup, evaluating different pretrained VAE-based representations' effects on OOD generalization.
result Many reinforcement learning agents are surprisingly robust to realistic distribution shifts, including sim-to-real cases.
Study questions the reliability of uncertainty quantification in evidential deep learning.
problem Reliability of uncertainty quantification in evidential deep learning.
method Analysis of evidential deep learning methods, revealing their limitations and interpreting them as out-of-distribution detection algorithms.
result EDL methods are unreliable in quantifying uncertainty, even when effective on downstream tasks.
Unsupervised meta-learning improves learning from small labeled data.
problem Acquiring representations from unlabeled data for effective downstream learning.
method Develops an unsupervised meta-learning method that optimizes for task learning ability from unlabeled data.
result Simple task construction mechanisms, like clustering embeddings, lead to good performance on various downstream tasks.
Develops UKP for comparing feature representations in multitask learning.
problem Comparing feature representations learned by different models without access to test data.
method Uniform Kernel Prober (UKP) for comparing representations in kernel ridge regression tasks.
result UKP provides a uniform measure of prediction error on test data without access to test data.
Proposes a new query autocompletion method that maximizes retrieval performance.
problem Users often select suboptimal queries due to unknown best retrieval performance.
method Formulates query autocompletion as ranking item rankings, uses counterfactual learning.
result Empirical results show improved query suggestions for better retrieval performance.