New methods evaluate data representations by complexity of low-loss predictor learning.
problem Evaluating quality of data representations for downstream tasks.
method Surplus Description Length (SDL) and ε Sample Complexity (εSC) methods.
result Methods measure the information needed to approximate optimal predictor up to specified tolerance.
New methods connect low-loss points on neural network surfaces.
problem Connecting low-loss points on neural network loss surfaces.
method Macroscopic distributional assumptions and global connection models.
result Accuracy correlates with complexity and sensitivity.
LoRA-Curve connects independent LoRA optima through continuous low-loss valleys, improving Bayesian model averaging.
problem Challenges in estimating epistemic uncertainty in LoRA-based Bayesian inference.
method Introduces LoRA-Curve, a segmented Bézier curve parameterization in the LoRA space, with free and anchored configurations.
result Empirically shows that connecting independent LoRA optima through continuous low-loss valleys improves mutual information of the predictive distribution.
How to model and encode the semantics of human-written text and select the type of neural network to process it are not settled issues in sentiment analysis. Accuracy and transferability are critical issues in machine learning in general. These properties are closely related to the loss estimates for the trained model.…
Proposes a method to ensure low losses across all subpopulations in large datasets.
problem Standard practice of minimizing average loss fails to guarantee low losses across all subpopulations in heterogeneous datasets.
method Convex procedure that controls worst-case performance over all subpopulations of a given size with finite-sample convergence guarantees.
result Empirically, the worst-case procedure learns models that do well against unseen subpopulations.
Novel approach embeds loss tunnels in neural networks, revealing insights into their structure.
problem Understanding the structure of neural network loss surfaces, especially low-loss tunnels.
method Directly embedding loss tunnels into the loss landscape of neural networks.
result Improved insights into the length and structure of loss tunnels, and better subspace inference in Bayesian neural networks.
Paper discovers simplicial complexes connecting trained models for improved ensembling.
problem Improving robustness and accuracy of deep learning ensembles.
method Identifies mode-connecting simplicial complexes on loss surfaces.
result Efficiently builds simplicial complexes for ensembling, outperforming independent ensembles.
Quantization-aware training can recover accuracy lost by post-training quantization.
problem Post-training quantization (PTQ) can fail sharply at aggressive bitwidths.
method A unified geometric framework that explains PTQ failure and QAT recovery.
result QAT has a useful bias that steers iterates back into the basin.
New framework for neural networks converging to low loss without overparameterization.
problem Training deep neural networks without overparameterization assumptions.
method Construction of random sparse lifts and analysis using algebraic topology and random graph theory.
result Provable convergence to low loss for large sparse neural networks.
Geodesics connect model modes in neural network loss landscapes.
problem Connecting modes in neural network loss landscapes.
method Reframed mode connectivity in Information Geometry, hypothesized geodesics as mode-connecting paths, proposed algorithm to approximate geodesics.
result Geodesics achieve mode connectivity in neural networks.
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.…
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.
The article compares predictor importance in classification problems with categorical outcomes.
problem Comparing predictor importance in classification problems with categorical response variables.
method The approach is based on the categorical Gini correlation (CGC) and tests differences in CGCs across predictor groups.
result The proposed methodology accommodates predictors of arbitrary and unequal dimensions and allows for dependence between predictor groups.
Flat-minima optimizers improve neural network generalization.
problem Improving neural network generalization performance.
method Stochastic Weight Averaging (SWA) and Sharpness-Aware Minimization (SAM).
result Surprising findings from loss surface analysis and broad benchmarking.
Paper proposes a sparse synthetic control method to select important predictors.
problem Choosing and weighting predictors affects synthetic control estimator performance.
method Sparse synthetic control procedure that penalizes predictors, derived in a linear factor model.
result Sparse synthetic control achieves lower bias and better post-treatment performance.
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…
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.
Proposes a method to create fair, robust predictors that remain consistent across different scenarios.
problem Creating fair and robust machine learning models that behave consistently across different scenarios.
method Graphical criteria and a model-agnostic framework called CIP based on HSCIC.
result Demonstrates the effectiveness of CIP in enforcing counterfactual invariance across various datasets.
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…
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.
Study shows competition feedback can make ML predictors biased towards specific user groups.
problem How competition affects machine learning predictors and user prediction quality.
method Flexible model of competing ML predictors, empirical and mathematical analysis.
result Competition causes predictors to specialize for specific sub-populations at the cost of general performance.
Study on merging predictors in causal and anticausal directions using CMAXENT.
problem Comparing merging predictors in causal and anticausal directions.
method Using CMAXENT as inductive bias, study differences in merging predictors.
result CMAXENT solution reduces to logistic regression in causal direction and LDA in anticausal direction.
Neural networks' optimization dynamics are confined to a single basin despite connected basins in the loss landscape.
problem Neural networks' optimization dynamics are confined to a single basin despite connected basins in the loss landscape.
method Identifying entropic barriers arising from the interplay between curvature variations along low-loss paths and noise in optimization dynamics.
result Curvature-induced entropic forces bias noisy dynamics back toward the endpoints, explaining the confinement and connectivity of solutions.
Paper introduces SUEL model for integrating predictors without labeled data.
problem Combining predictors with unknown accuracy and high correlation.
method Structured unsupervised ensemble learning (SUEL) with correlation-based decomposition algorithms.
result Efficient integration of dependent predictors without labeled data.
The paper develops predictors for functional data on manifolds.
problem Functional data prediction on time-varying manifolds.
method Least-squares local linear Fréchet curve predictor and weighted Fréchet mean approach.
result Asymptotical optimality of the proposed predictors.
Adaptive kernels from neural networks improve model performance.
problem Improving neural network performance through adaptive kernels.
method Deriving adaptive kernels from infinite-width neural networks using feature learning and gradient flow training.
result Adaptive kernels achieve lower test loss compared to traditional kernels.
Random Feature (RF) models are used as efficient parametric approximations of kernel methods. We investigate, by means of random matrix theory, the connection between Gaussian RF models and Kernel Ridge Regression (KRR). For a Gaussian RF model with P features, N data points, and a ridge λ, we show that the avera…
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.
LESS combines local predictors for subsets to learn from heterogeneous input-output pairs.
problem Learning from heterogeneous input-output pairs in populations with varied behavior.
method LESS algorithm: generates subsets, trains local predictors, combines them.
result LESS is highly competitive compared to state-of-the-art methods.
Paper proposes SDDP for improving time series forecasting with high-dimensional predictors.
problem Improving time series forecasting with high-dimensional predictors.
method SDDP framework that incorporates target variable and lagged observations into factor extraction process.
result SDDP improves predictive accuracy in time series forecasting.
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.
Neurosymbolic predictors fail to model uncertainty under independence assumption.
problem Neurosymbolic predictors' reliance on independence assumption limits their ability to model uncertainty.
method Formal analysis of NeSy predictors under independence assumption.
result Assuming independence among symbolic concepts prevents NeSy predictors from representing uncertainty.
GATES improves neural architecture search by modeling operations as information transformation.
problem Improving predictor-based neural architecture search efficiency.
method GATES models operations as information transformation, covering both node and edge cell search spaces.
result GATES boosts sample efficiency and improves predictor performance.
AM-PPI uses multiple predictors to reduce label cost in healthcare AI.
problem Reduces label cost in post-deployment monitoring of healthcare AI.
method Combines model predictions with a small labeled sample, routing each instance to a cost-appropriate subset of predictors.
result Produces narrower confidence intervals than single-predictor methods.
New loss function reduces outage probability in ML-assisted resource allocation.
problem Minimizing outage probability in ML-assisted resource allocation systems.
method Developed a novel loss function and trained an ML model to address the outage probability challenge.
result Exact and asymptotic expressions for the system's outage probability were established.
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.
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.
Post-processing predictors reduces calibration errors for decision-making.
problem Predictors with low calibration error for machine learning may have high error for decision-making.
method Post-processing with ε distance to calibration adds noise to make predictions differentially private.
result Post-processing achieves O(√ε) ECE and CDL, asymptotically optimal.
A new method controls risk for set predictors using cross-validation.
problem Inefficient set predictors when data limited.
method Cross-validation conformal risk control (CV-CRC).
result CV-CRC offers theoretical guarantees and reduces set size.
A new method accounts for predictor dependencies in XAI feature rankings.
problem Assumption of predictor independence in XAI methods leads to unreliable feature rankings.
method Proposes a proxy method to modify XAI outcomes considering predictor dependencies.
result Allows more accurate feature ranking in models with correlated predictors.
New theory validates the use of invariant predictors for OOD generalization.
problem Ensuring predictors generalize well across unseen environments.
method Developed new theoretical conditions and derived an Inter Gradient Alignment algorithm.
result Validated the necessity of invariant predictors for OOD optimality.
Understanding optimal prompts for binary sequence predictors is challenging.
problem Finding good prompts for binary sequence predictors is difficult.
method Viewing prompting as finding the best conditioning sequence on a near-optimal sequence predictor, using empirical and statistical analysis.
result Optimal prompts can be better understood given the pretraining distribution, which is not usually available.
Optimal trading strategy with predictor and costs, derived equations and shape.
problem Optimal trading strategy in presence of price predictor, costs, and risk control.
method Path-integral method to derive equations for band edges, solved explicitly for Ornstein-Uhlenbeck predictor.
result Explicit equations and shape of the optimal band strategy derived and analyzed.
There are many surprising and perhaps counter-intuitive properties of optimization of deep neural networks. We propose and experimentally verify a unified phenomenological model of the loss landscape that incorporates many of them. High dimensionality plays a key role in our model. Our core idea is to model the loss la…
In this work, we study the problem of aggregating a finite number of predictors for nonstationary sub-linear processes. We provide oracle inequalities relying essentially on three ingredients: (1) a uniform bound of the ℓ1 norm of the time varying sub-linear coefficients, (2) a Lipschitz assumption on the predict…
New sample complexity bounds for linear predictors and neural networks, focusing on initialization.
problem Understanding sample complexity for vector-valued linear predictors and neural networks, especially under initialization-dependent conditions.
method Size-independent bounds on Frobenius norm distance from a fixed reference matrix, applying to vector-valued predictors and neural networks.
result Established new sample complexity bounds for feed-forward neural networks, resolving open questions and introducing a new learnable problem.
Efficiency criteria improve conformal predictors' performance.
problem Improving the performance of conformal predictors.
method Learning classifiers by minimizing observed fuzziness as a training objective function.
result Conformal predictors trained by minimizing observed fuzziness perform better than traditional ones.