Linear properties are either universal or absent across language models.
problem Explaining the prevalence of linear properties in language models.
method Proved identifiability of distribution-equivalent next-token predictors and analyzed various notions of linearity.
result Linear properties either hold in all or none distribution-equivalent next-token predictors.
This paper continues study, both theoretical and empirical, of the method of Venn prediction, concentrating on binary prediction problems. Venn predictors produce probability-type predictions for the labels of test objects which are guaranteed to be well calibrated under the standard assumption that the observations ar…
Study shows NCCP can replace CP for ACI in non-exchangeable data.
problem Ensuring reliable prediction under non-exchangeability.
method Demonstrates NCCP as a valid alternative to CP for ACI.
result NCCP offers computational advantages and comparable predictive efficiency.
The problem of forecasting conditional probabilities of the next event given the past is considered in a general probabilistic setting. Given an arbitrary (large, uncountable) set C of predictors, we would like to construct a single predictor that performs asymptotically as well as the best predictor in C, on any data.…
This paper proposes a new algorithmic framework, predictor-verifier training, to train neural networks that are verifiable, i.e., networks that provably satisfy some desired input-output properties. The key idea is to simultaneously train two networks: a predictor network that performs the task at hand,e.g., predicting…
Paper introduces a method to predict molecule properties from diverse data sources.
problem Limited ability to accommodate scarce or fragmented training data.
method Adaptive Invariance using invariant risk minimization to generalize beyond heterogeneous data.
result Predictor outperforms state-of-the-art transfer learning methods by significant margin.
Study tail risk in high-frequency finance using L1-regularized regression.
problem Measuring tail risk dynamics in high-frequency financial markets.
method Dynamic extreme value regression model with L1-regularized maximum likelihood estimator. result Severity of extreme losses well predicted by low price impact in high volatility periods.
Scaffolding sets improve predictor correctness across subsets.
problem Ensuring predictor correctness across multiple subsets.
method Inspired by neural nets, constructing scaffolding sets to ensure correctness.
result Scaffolding sets ensure predictor correctness, not just calibration.
This paper presents Sparse Partitioning, a Bayesian method for identifying predictors that either individually or in combination with others affect a response variable. The method is designed for regression problems involving binary or tertiary predictors and allows the number of predictors to exceed the size of the sa…
Derives bounds for deterministic predictors using smooth loss functions.
problem Generalizing probabilistic predictors to deterministic ones.
method Exploits smoothness properties of loss and predictor classes, controlling the Jensen gap class through Rademacher complexity.
result Derives bounds for deterministic predictors involving flatness quantities from Jacobians and Hessians.
The study addresses biases in evaluating molecular optimization methods and proposes methods to reduce these biases.
problem Biases in in silico evaluation of molecular optimization methods.
method Discussion and empirical investigation of bias reduction methods for predictor misspecification and sample reuse.
result Empirical investigation of bias reduction methods for predictor misspecification and sample reuse.
Adversarial training achieves optimal test error for shallow networks.
problem Achieving optimal adversarial test error for general data distributions.
method Applying new Rademacher complexity bounds and properties of optimal adversarial predictors.
result Adversarial training can achieve optimal adversarial test error for general data distributions.
Novel strategy for federated learning with privacy-preserving predictors and nonvacuous generalization bounds.
problem Privacy-preserving federated learning with nonvacuous generalization bounds.
method Randomized predictors, PAC-Bayesian generalization bound, synchronous and heterogeneous/homogenous cases.
result Achieves comparable predictive performance to batch approach while preserving privacy.
The paper proposes multicalibration to improve matching in graphs with imperfect predictors.
problem Finding the best matching in graphs with imperfect predictors.
method Introduces multicalibration as a fairness notion to ensure unbiasedness on protected sets of contexts.
result Constructing a multicalibrated predictor that outperforms standard optimal rules in matching algorithms.
We provide a new approach to training neural models to exhibit transparency in a well-defined, functional manner. Our approach naturally operates over structured data and tailors the predictor, functionally, towards a chosen family of (local) witnesses. The estimation problem is setup as a co-operative game between an …
WeakNAS uses a set of weaker predictors to find top architectures with fewer samples.
problem Finding the best neural architecture with heavy computation costs.
method Proposes a paradigm shift from fitting the whole architecture space to progressively fitting a search path through a set of weaker predictors.
result WeakNAS produces coarse-to-fine iteration to gradually refine the ranking of sampling space, requiring fewer samples to find top-performance architectures.
Derandomizing PAC-Bayes bounds for smooth loss functions
problem Derandomizing PAC-Bayes bounds for smooth loss functions
method Exploiting smoothness properties of both the loss and the predictor class
result Bounds for deterministic predictors that involve flatness quantities
Group model selection is the problem of determining a small subset of groups of predictors (e.g., the expression data of genes) that are responsible for majority of the variation in a response variable (e.g., the malignancy of a tumor). This paper focuses on group model selection in high-dimensional linear models, in w…
Although there is a rich literature on methods for allowing the variance in a univariate regression model to vary with predictors, time and other factors, relatively little has been done in the multivariate case. Our focus is on developing a class of nonparametric covariance regression models, which allow an unknown p …
We resolve the open problem of optimal sample complexity for multicalibration and deterministic predictors.
problem Optimal sample complexity for multicalibration and deterministic predictors
method Minimax-optimal multicalibration algorithm and generalization to OI predictors
result Minimax-optimal multicalibration algorithm and deterministic predictors with optimal sample complexity
We propose a penalized orthogonal-components regression (POCRE) for large p small n data. Orthogonal components are sequentially constructed to maximize, upon standardization, their correlation to the response residuals. A new penalization framework, implemented via empirical Bayes thresholding, is presented to effecti…
Study shows interpolating predictor's risk is optimal in low-dimensional factor regression models.
problem Understanding the risk of interpolating predictors in high-dimensional factor regression models.
method Detailed finite-sample analysis of minimum-norm interpolating predictor's risk in factor regression models.
result The risk of the minimum-norm interpolating predictor approaches optimal benchmarks in low-dimensional factor regression models.
The paper analyzes bagging in overparameterized learning, deriving risk properties and optimal subsample sizes.
problem Characterizing the risk of bagged predictors in overparameterized settings.
method General strategy using classical results on simple random sampling, specialized for ridge and ridgeless predictors.
result Derives exact asymptotic risk of bagged ridge and ridgeless predictors under various conditions.
Paper proposes a self-training method to generate molecular targets.
problem Challenges in training generative models for complex molecular design.
method Iterative target augmentation using a property predictor and EM iterations.
result Significant gains in molecular design, outperforming previous methods.
Study calibrates high-dimensional binary classifiers using angle between estimator and true weights.
problem Calibrating high-dimensional binary classifiers with provable properties.
method Interpolates with a chance classifier to construct well-calibrated predictor based on angle between estimator and true weights.
result Angular calibration approach is provably well-calibrated in high dimensions, minimizing Bregman divergence.
Optimizing proper loss yields calibrated models under specific conditions.
problem Understanding when optimizing proper loss functions leads to calibrated predictions.
method Local optimality condition and Lipschitz functions.
result Predictors with local optimality are nearly calibrated and nearly locally optimal.
Gas demand is made of three components: Residential, Industrial, and Thermoelectric Gas Demand. Herein, the one-day-ahead prediction of each component is studied, using Italian data as a case study. Statistical properties and relationships with temperature are discussed, as a preliminary step for an effective feature s…
The paper studies calibration in ML models for wireless networks, showing key theoretical and practical insights.
problem Ensuring ML models in wireless networks deliver well-calibrated confidence scores for reliable decision-making.
method Theoretical analysis and simulation-based experiments using Platt scaling and isotonic regression.
result Well-calibrated models improve the system's minimum achievable OP and are part of a broader class of predictors.
New bounds show linear predictors rarely overfit with certain optimization methods.
problem Bounding test error for linear predictors with stochastic optimization methods.
method Coupling argument for fixed point methods like stochastic and batch mirror descent.
result Locally-adapted rates that depend on predictor properties, not global problem structure.
In order to identify important variables that are involved in making optimal treatment decision, Lu et al. (2013) proposed a penalized least squared regression framework for a fixed number of predictors, which is robust against the misspecification of the conditional mean model. Two problems arise: (i) in a world of ex…
Tabular in-context learners perform well on biomolecular tasks, but performance depends on the representation used.
problem Predicting biomolecular properties from limited labeled data.
method Evaluating tabular in-context learners on protein fitness regression and small-molecule classification tasks.
result Tabular in-context learners are competitive for protein fitness regression but not for small-molecule classification.
A new model for learning and unlearning predictors efficiently.
problem Learning and unlearning predictors from subsets of data.
method Proposes a ticketed model for learning-unlearning, allowing examples to present tickets for unlearning.
result Space-efficient schemes for various concept classes, including thresholds and parities.
A critical decision point when training predictors using multiple studies is whether studies should be combined or treated separately. We compare two multi-study prediction approaches in the presence of potential heterogeneity in predictor-outcome relationships across datasets: 1) merging all of the datasets and traini…
New truthful calibration errors improve model ranking in multiclass prediction.
problem Non-truthful calibration errors can mislead model comparisons.
method Introduced perfectly truthful calibration errors for multiclass predictions.
result Truthful calibration errors preserve decision-theoretic dominance and stabilize model rankings.
Deep neural networks improve AFT model for non-linear predictors.
problem Nonlinearity in predictors of AFT models.
method Apply DNNs to fit AFT models using Gehan-type loss and sub-sampling.
result DeepR-AFT outperforms parametric and semiparametric models.
New method learns optimal prediction strategies in adversarial games.
problem Learning optimal prediction procedures in uncertain data environments.
method Adversarial Monte Carlo approach with neural network architecture.
result Optimal strategy is equivariant and invariant to various transformations.
Decision trees are consistent for regression and classification tasks even with many predictors.
problem Consistency of decision trees with many predictors.
method CART and C4.5 methodology, oracle inequality, sparsity constraints.
result Decision trees and random forests are consistent for various types of data.
A predictor improves power grid frequency forecasts up to one hour.
problem Improving frequency forecast for better power system stability.
method Developed a weighted-nearest-neighbor (WNN) predictor.
result Forecasts for up to one hour are more precise than averaged daily profiles.
The study simplifies assessing overlap in logistic regression models using empirical likelihood.
problem Assessing overlap in multidimensional logistic regression models.
method Translation of Silvapulle's condition to empirical likelihood maximization, mechanized with R code.
result Minimal overlapping structures are cataloged in dimensions less than four, providing rules for higher dimensions.
Interactive visualization helps understand complex machine learning models.
problem Low interpretability of machine learning models.
method Interactive slice visualization of predictor space, using interaction or touring algorithms.
result Enhances understanding and validation of machine learning model fits.
We give examples of data-generating models under which Breiman's random forest may be extremely slow to converge to the optimal predictor or even fail to be consistent. The evidence provided for these properties is based on mostly intuitive arguments, similar to those used earlier with simpler examples, and on numerica…
Recent results in the literature indicate that a residual network (ResNet) composed of a single residual block outperforms linear predictors, in the sense that all local minima in its optimization landscape are at least as good as the best linear predictor. However, these results are limited to a single residual block …
PEER tackles multi-response regression with incomplete outcomes efficiently.
problem Challenges in estimating, predicting, and computing with large-scale multi-response regression and incomplete outcomes.
method PEER converts multi-response regression into parallel univariate-response regressions.
result PEER achieves consistency in estimation, prediction, and variable selection.
Timely assessment of compound toxicity is one of the biggest challenges facing the pharmaceutical industry today. A significant proportion of compounds identified as potential leads are ultimately discarded due to the toxicity they induce. In this paper, we propose a novel machine learning approach for the prediction o…
New bounds explain deterministic non-smooth deep nets without large Lipschitz constants.
problem Challenges in explaining generalization of deterministic non-smooth deep nets.
method De-randomized PAC-Bayes margin bounds for deterministic non-convex and non-smooth predictors.
result New bounds avoid large Lipschitz constants, providing generalization guarantees.
This paper proposes a method to reduce complexity in GLMs with categorical predictors.
problem Wasteful, hard-to-interpret, and prone to overfitting of traditional one-hot encoding for high-cardinality categorical predictors.
method Clustering categories of categorical predictors through a numerical method that preserves or improves accuracy while reducing the number of coefficients.
result Clustering categories of categorical predictors reduces complexity substantially without harming accuracy.
New robust estimator improves variable selection and coefficient estimation in linear regression with heavy-tailed errors and outliers.
problem Heavy-tailed errors and anomalous predictors in high-dimensional regression.
method Adaptive PENSE estimator for robust variable selection and estimation.
result Adaptive PENSE estimator provides reliable results even under very heavy-tailed errors and aberrant predictors.
New bounds prevent degradation in high-dimensional signal estimation.
problem Statistical learning bounds degradation with increasing dimensionality.
method Investigates linear prediction rules under structural assumptions.
result Derives upper and lower bounds on generalization error.