New method evaluates LLMs fairness in universal prediction.
problem Evaluating fairness of large language models in universal prediction.
method Introducing batch regret as a modification of average regret for LLMs.
result Asymptotical value of batch regret for add-constant predictors on memoryless and first-order Markov sources.
Universal online optimization for dynamic environments using uniclass prediction.
problem Online optimization in changing environments with dynamic regret.
method Reduces dynamic online optimization to uniclass prediction problem, allowing control over dynamic regret bounds.
result First paper with state-of-the-art dynamic regret guarantees for general convex cost functions.
Exact distribution of split conformal prediction coverage found.
problem Determining the reliability of prediction sets in batch mode.
method Analysis of exchangeable data to find universal distribution of empirical coverage.
result Exact distribution of empirical coverage is universal and determined by nominal miscoverage level and calibration sample size.
The paper derives a new theorem for predicting batches of data.
problem Finding lower bounds on minimal batch regret.
method Derives a conditional version of the regret-capacity theorem.
result Reveals a connection between conditional Rényi divergence and conditional Sibson's mutual information.
The Bayesian framework is a well-studied and successful framework for inductive reasoning, which includes hypothesis testing and confirmation, parameter estimation, sequence prediction, classification, and regression. But standard statistical guidelines for choosing the model class and prior are not always available or…
PanRep learns universal node embeddings for heterogeneous graphs.
problem Learning universal node embeddings for heterogeneous graphs.
method Graph Neural Network (GNN) model with four decoders capturing different properties.
result PanRep outperforms unsupervised and supervised methods in node classification and link prediction.
Universal supervised learning is considered from an information theoretic point of view following the universal prediction approach, see Merhav and Feder (1998). We consider the standard supervised "batch" learning where prediction is done on a test sample once the entire training data is observed, and the individual s…
GNP models predictive correlations and outperforms NPs.
problem Training and understanding of Neural Processes.
method Proposed a new model, Gaussian Neural Process (GNP), which incorporates translation equivariance and provides universal approximation guarantees.
result Demonstrates encouraging performance and provides universal approximation guarantees.
UTOPIA aggregates multiple prediction intervals efficiently.
problem Constructing optimal prediction intervals for various real-world data problems.
method UTOPIA is a universally trainable strategy using linear or convex programming.
result UTOPIA constructs prediction intervals with small average width and high coverage probability.
Universal preconditioning reduces sequential prediction regret.
problem Improving sequential prediction performance.
method Convolve target sequence with orthogonal polynomial coefficients.
result First sublinear and hidden-dimension-independent regret bounds.
This paper fine-tunes LLMs for stock return prediction using financial news.
problem Improving stock return forecasting accuracy using LLMs.
method Fine-tuning LLMs with text and forecasting modules, comparing encoder-only and decoder-only models, and integrating token-level representations.
result LLMs' aggregated token-level embeddings enhance return predictions for long-only and long-short portfolios.
Paper presents a universal baseline for binary prediction models.
problem Need a robust baseline to evaluate model performance.
method Dutch Draw (DD) baseline method for binary classification models.
result Reduces to almost always predicting zero or one in most situations.
Develops a new method for online conformal prediction without manual tuning.
problem Achieving long-run 1−α coverage for arbitrary data streams in an informative manner. method Linearized regret theory and universal portfolio algorithms.
result Strong finite-time bounds on miscoverage for UP-OCP, outperforming prior methods.
Efficiently constructs prediction bands with minimal assumptions.
problem Uncertainty quantification for nonparametric, heteroscedastic data.
method Semi-definite programming for data-adaptive prediction bands.
result Strong non-asymptotic coverage properties with minimal distributional assumptions.
In this article, a large data set containing every course taken by every undergraduate student in a major university in Canada over 10 years is analysed. Modern machine learning algorithms can use large data sets to build useful tools for the data provider, in this case, the university. In this article, two classifiers…
OptFormer learns universal HPO from diverse datasets.
problem Learning HPO from experiments with different hyperparameters.
method Text-based Transformer framework for joint policy and function prediction.
result OptFormer can imitate multiple HPO algorithms and improve predictions.
A new machine-learned CG model predicts protein structures efficiently.
problem Developing a universal, computationally efficient protein simulation model.
method Combining deep learning with all-atom protein simulations to create a transferable CG force field.
result The model predicts protein structures, intermediates, and fluctuations efficiently.
New framework predicts crypto volatility, outperforming traditional models.
problem Forecasting volatility in cryptocurrencies during the crypto-winter.
method Combines LSTM and rough volatility models, using a parsimonious parametric model.
result Similar prediction performances with fewer parameters, suggesting universality of volatility mechanisms.
Using a large-scale Deep Learning approach applied to a high-frequency database containing billions of electronic market quotes and transactions for US equities, we uncover nonparametric evidence for the existence of a universal and stationary price formation mechanism relating the dynamics of supply and demand for a s…
Adversarial examples are inputs intentionally perturbed with the aim of forcing a machine learning model to produce a wrong prediction, while the changes are not easily detectable by a human. Although this topic has been intensively studied in the image domain, classification tasks in the audio domain have received les…
The paper demonstrates that falsifiability is fundamental to learning. We prove the following theorem for statistical learning and sequential prediction: If a theory is falsifiable then it is learnable -- i.e. admits a strategy that predicts optimally. An analogous result is shown for universal induction.
While deep learning is remarkably successful on perceptual tasks, it was also shown to be vulnerable to adversarial perturbations of the input. These perturbations denote noise added to the input that was generated specifically to fool the system while being quasi-imperceptible for humans. More severely, there even exi…
The Predictive Normalized Maximum Likelihood (pNML) scheme has been recently suggested for universal learning in the individual setting, where both the training and test samples are individual data. The goal of universal learning is to compete with a ``genie'' or reference learner that knows the data values, but is res…
Study high-dimensional logistic regression with missing data, providing exact error characterizations.
problem High-dimensional logistic regression with missing or corrupted covariates.
method Exact characterizations of prediction and estimation errors under independence and moment conditions.
result Characterizations are universal and hold for various imputation strategies.
Signatures of universality are detected by comparing individual eigenvalue distributions and level spacings from financial covariance matrices to random matrix predictions. A chopping procedure is devised in order to produce a statistical ensemble of asset-price covariances from a single instance of financial data sets…
GemNet improves molecular predictions by overcoming graph neural network limitations.
problem Graph neural networks struggle with distinguishing certain types of molecular graphs.
method Discretized geometric message passing neural network (GemNet) with spherical representations.
result GemNet outperforms previous models on molecular datasets by 34-20%.
A universal collection of 4 invariants improves neural network accuracy for molecular dynamics.
problem Improving accuracy of neural networks in molecular dynamics.
method Developed a universal collection of 4 smooth scalar invariants on M(3) x M(3) and evaluated their effectiveness in a PONITA neural network architecture.
result Using a universal collection of invariants significantly improves neural network accuracy.
This research formalizes uncertainty quantification for Universal Differential Equations models.
problem Quantifying uncertainties in Universal Differential Equations models.
method Formalized uncertainty quantification methods for UDEs, including frequentist and Bayesian approaches.
result Evaluation of ensemble, variational inference, and MCMC sampling methods for UDEs.
FLASH-MAX predicts electromagnetic fields from sparse data in seconds.
problem Predicting homogeneous electromagnetic fields from sparse pointwise observations.
method Exact-by-construction neural network architecture that satisfies Maxwell's equations symbolically.
result FLASH-MAX achieves sub-1% relative validation error from 1K sparse observations in seconds.
The goal of this paper is to characterize function distributions that deep learning can or cannot learn in poly-time. A universality result is proved for SGD-based deep learning and a non-universality result is proved for GD-based deep learning; this also gives a separation between SGD-based deep learning and statistic…
Transformers enable in-context learning with guarantees for a wide range of tasks.
problem How to enable in-context learning with transformers for various tasks.
method Developed a universal approximation theory integrating Barron's function approximation with transformer capabilities.
result Transformers can approximate any target function with vanishingly small risk using a few in-context examples.
New approach tackles decision-making under predictions that shape outcomes.
problem Challenges in learning optimal decision rules when predictions influence outcomes.
method Introduces performative omniprediction, a predictor that encodes optimal decision rules for multiple objectives.
result Efficient performative omnipredictors exist under a natural restriction of outcome performativity.
Universal AI seeks high-optionality states through empowerment and curiosity.
problem Understanding and optimizing AI behavior in uncertain environments.
method Unified framework combining AIXI and variational empowerment, showing how universal AI agents balance goal-directed behavior with uncertainty reduction curiosity.
result Self-AIXI asymptotically converges to AIXI performance and exhibits power-seeking behavior due to intrinsic motivations.
The study finds cash productivity predicts stock performance in a specific subset of firms.
problem Predicting future stock performance using cash productivity.
method Using financial and market data, calculated cash returns as a proxy for operational efficiency, and tested a long-only strategy on Nasdaq-listed non-financial firms.
result Cash productivity has significant predictive power in a handpicked portfolio but limited across the broader Nasdaq universe.
Transfer learning improves chaotic dynamics predictions with less data.
problem Efficiently predicting chaotic dynamics with limited data.
method Transfer learning for nonlinear dynamics, optimizing transfer rate and leveraging small-scale turbulence universality.
result Significantly more accurate inference of chaotic dynamics achieved.
The book explores universal time-series forecasting using mixture predictors.
problem Sequential probability forecasting in a general setting.
method Mixture predictors combining multiple predictors.
result Universality of mixture predictors in a general probabilistic setting.
We use methods of random matrix theory to analyze the cross-correlation matrix C of price changes of the largest 1000 US stocks for the 2-year period 1994-95. We find that the statistics of most of the eigenvalues in the spectrum of C agree with the predictions of random matrix theory, but there are deviations for a fe…
New analysis shows halting time is predictable for large models, improving optimization efficiency.
problem Understanding the average-case complexity of optimization algorithms for large-scale models.
method Average-case analysis of first-order methods on random least squares and neural networks.
result Halting time is independent of input distribution, leading to tighter convergence rates.
Generalized algorithm for translation and scale-invariant prediction.
problem Sequential prediction with expert advice, focusing on translation and scale invariance.
method Designing a generalized online algorithm using the universal prediction perspective to compete against a generic class of expert selection strategies.
result No preliminary knowledge of loss sequences is required; performance bounds are stable under arbitrary scalings and translations.
Two new methods generate probabilistic forecasts of individual treatment effects.
problem Generating probabilistic forecasts of individual treatment effects for risk-aware decision-making.
method Proposes CCT and CMC meta-learners combining conformal predictive systems with analytic convolution or Monte Carlo sampling.
result Achieve probabilistically calibrated predictive distributions and performant continuous ranked probability scores.
UNOT solves optimal transport problems efficiently using neural networks.
problem Computational expense in solving optimal transport problems.
method UNOT (Universal Neural Optimal Transport) uses Fourier Neural Operators to predict OT distances and plans accurately and efficiently.
result UNOT achieves up to 7.4x speedup over the Sinkhorn algorithm while maintaining accuracy.
DeepRSCN models nonlinear systems using stochastic configurations.
problem Modeling nonlinear dynamic systems efficiently.
method Incrementally constructed deep reservoir computing framework with random parameters and online weight updates.
result DeepRSCN outperforms single-layer networks in efficiency, learning, and generalization.
We present a simple and general result that the sign of the variations or increments of uncorrelated times series are predictable with a remarkably high success probability of 75% for symmetric sign distributions. The origin of this paradoxical result is explained in details. We also present some tests on synthetic, fi…
Throughout science and technology, receiver operating characteristic (ROC) curves and associated area under the curve (AUC) measures constitute powerful tools for assessing the predictive abilities of features, markers and tests in binary classification problems. Despite its immense popularity, ROC analysis has been su…
This is a survey on known results and open problems about closed aspherical manifolds, i.e., connected closed manifolds whose universal coverings are contractible. Many examples come from certain kinds of non-positive curvature conditions. The property aspherical which is a purely homotopy theoretical condition implies…
DebiNet uses over-parameterized neural networks to improve linear model performance and debiasing.
problem Improving linear model performance and debiasing in high-dimensional settings.
method Incorporates over-parameterized neural networks into semi-parametric models to estimate parameters consistently.
result DebiNet offers valid inference and accurate prediction by leveraging neural networks' universal approximation and linear model's interpretability.
Develops optimal decision-making framework for uncertain counterfactuals.
problem Ensuring reliability of predictions in high-stakes decisions.
method Policy-Coupled Risk-Averse Conformal Prediction (PC-RACP).
result Optimal prediction sets for counterfactual decisions with valid coverage.
New methods for inferring, predicting, and estimating continuous-time, discrete-event processes.
problem Inferring, predicting, and estimating entropy rate of continuous-time, discrete-event processes.
method Bayesian structural inference extended with neural networks.
result Methods are competitive for prediction and entropy-rate estimation with state-of-the-art.