Paper analyzes weak-to-strong generalization in CNNs, identifying data-scarce and data-abundant regimes.
problem Weak-to-strong generalization in CNNs trained on weak models.
method Formal analysis of gradient descent dynamics in data-scarce and data-abundant regimes.
result Identifies two regimes and distinct mechanisms of generalization in each.
Sparse random features improve accuracy in data-scarce settings.
problem Limited accuracy of random feature methods in data-scarce applications.
method Sparse random feature expansion using compressive sensing.
result Improved generalization bounds for sparse random features.
Proposes a method to improve treatment policies in data-scarce clinical settings.
problem Improving treatment policies in data-scarce clinical settings with unobserved confounding.
method Uses a causal mechanism to model the underlying generative process and augments counterfactual trajectories with source domain priors.
result Significantly improves treatment policy performance in a simulated sepsis treatment task.
This work improves trace norm regularization for multi-task learning with limited data.
problem Learning from few samples across multiple tasks.
method Trace norm regularization for a linear shared representation model.
result First estimation error bound for trace norm regularized estimator with scarce data.
We describe a method to identify poor households in data-scarce countries by leveraging information contained in nationally representative household surveys. It employs standard statistical learning techniques---cross-validation and parameter regularization---which together reduce the extent to which the model is over-…
New framework improves fairness in small data settings.
problem Ensuring fairness in low-data environments.
method Combines posterior sampling exploration with fair classification.
result Framework maximizes accuracy while meeting fairness constraints.
New ASR system handles multiple languages without needing language-specific encoding.
problem Joint training of data-rich and data-scarce languages in a single model.
method Transforms all languages to a single writing system through transliteration, separating modeling and rendering.
result Language-agnostic multilingual ASR system reduces WER up to 10% over language-dependent models.
Flood forecasts are crucial for effective individual and governmental protective action. The vast majority of flood-related casualties occur in developing countries, where providing spatially accurate forecasts is a challenge due to scarcity of data and lack of funding. This paper describes an operational system provid…
Parameter inference in ordinary differential equations is an important problem in many applied sciences and in engineering, especially in a data-scarce setting. In this work, we introduce a novel generative modeling approach based on constrained Gaussian processes and leverage it to build a computationally and data eff…
b-LOAD extends local causal discovery with prior knowledge, improving causal effect estimation.
problem Local causal discovery struggles in data-scarce settings due to uncertainty and incomplete neighborhoods.
method b-LOAD incorporates prior knowledge directly into local structure learning, using Meek's rules to refine discovery.
result b-LOAD refines the admissible equivalence class and enlarges identifiable causal queries, improving causal effect estimation.
Transformer model outperforms classical methods in childhood anemia prediction across diverse countries.
problem Generalizing childhood anemia prediction models across different countries and data scarcity.
method Transformer-based tabular foundation model compared to classical supervised methods using DHS data.
result Transformer model achieves lower Brier score and ECE in low-data settings, outperforming classical models.
New method combines long-memory reservoirs for accurate dengue forecasting from short data.
problem Accurate dengue forecasting from short, noisy, non-stationary, and nonlinear data.
method Fractional ESN and Wavelet ESN frameworks integrating long-term memory.
result fESN and wESN outperform baselines in multiple dengue datasets and forecasting horizons.
Recently, deep models have been successfully applied in several applications, especially with low-level representations. However, sparse, noisy samples and structured domains (with multiple objects and interactions) are some of the open challenges in most deep models. Column Networks, a deep architecture, can succinctl…
ML models predict water table depth more accurately than PB models, especially in data-scarce regions.
problem Uncertainty in large-scale simulations of water table depth due to biased observational data and model flexibility.
method Constructed three ML models using XGBoost and over 20 million real and proxy observations across the US and Canada.
result ML models correlate 0.6-0.75 with real and proxy observations, significantly better than PB models (0.21-0.40).
A new method combines multiple bounds and betting strategies for selective prediction, improving risk coverage in data-scarce settings.
problem Selective prediction with risk control in data-scarce domains.
method Combines concentration inequalities, multiple-testing corrections, and betting-based confidence sequences.
result Transfer-Informed Betting achieves tighter bounds and better coverage in data-scarce settings.
Develops methods to simulate rare transitions in molecular systems.
problem Rare transitions between metastable states in molecular systems are difficult to study due to limited data.
method Two novel methods: chain-based and midpoint-based approaches.
result Demonstrates effectiveness of methods in both data-rich and data-scarce scenarios.
New method improves uncertainty estimation in Bayesian deep learning models.
problem Underestimation of predictive uncertainty in Neural Linear Models (NLMs).
method Proposes a novel training method to capture useful predictive uncertainties and incorporate domain knowledge.
result Traditional training procedures for NLMs can drastically underestimate uncertainty in data-scarce regions.
New method sparsifies hybrid neural ODEs for better performance and stability.
problem Excessive latent states and interactions from mechanistic models lead to training inefficiency and over-fitting.
method Automatic state selection and structure optimization combining domain-informed graph modifications with data-driven regularization.
result Improved predictive performance and robustness with desired sparsity.
The problem of feature disentanglement has been explored in the literature, for the purpose of image and video processing and text analysis. State-of-the-art methods for disentangling feature representations rely on the presence of many labeled samples. In this work, we present a novel method for disentangling factors …
NeuralSurv models survival analysis with Bayesian uncertainty.
problem Capturing time-varying risk relationships in survival analysis.
method Two-stage data-augmentation scheme, mean-field variational algorithm, coordinate-ascent updates, locally linearized Bayesian neural network.
result Delivers superior calibration compared to state-of-the-art models.
TabPFN doesn't outperform GLM and XGBoost for motor insurance pricing.
problem Improving insurance pricing models using Tabular Foundation Models (TFMs).
method Pre-training on synthetic datasets and in-context learning for inference.
result TabPFN does not consistently outperform established baselines, has longer inference times, and is sensitive to training set size.
CoLoRA models predict PDE solutions quickly and accurately with minimal data.
problem Efficiently modeling PDE solutions with limited data.
method Continuous low-rank adaptation of neural networks trained on offline data.
result Predictions are orders of magnitude faster and more accurate than classical methods.
Treating neural network inputs and outputs as random variables, we characterize the structure of neural networks that can be used to model data that are invariant or equivariant under the action of a compact group. Much recent research has been devoted to encoding invariance under symmetry transformations into neural n…
Stabilizes policy optimization with off-policy data using divergence augmentation.
problem Premature convergence and instability in policy optimization with off-policy data.
method Incorporates Bregman divergence between behavior and current policies to ensure safe policy updates.
result Empirically shows better performance in data-scarce scenarios compared to other algorithms.
XIMP improves molecular property prediction by integrating multiple graph representations.
problem Graph neural networks struggle in data-scarce regimes and fail to surpass traditional methods.
method Cross-graph inter-message passing with multiple graph abstractions.
result XIMP outperforms state-of-the-art baselines across diverse molecular property tasks.
Optimal feature transfer identified through bias-variance analysis.
problem Optimizing feature transfer in transfer learning.
method Simple linear model with fine-grained bias-variance decomposition.
result Optimal pretrained feature transform is naturally sparse.
SPI uses synthetic data to improve predictive inference efficiency.
problem Inefficient predictive inference with scarce calibration data.
method Integrates synthetic data to align nonconformity scores and improve coverage guarantees.
result SPI yields substantially tighter and more informative prediction sets.
MetaCaDI learns causal graphs and unknown interventions from few data instances.
problem Discovering causal mechanisms in systems with high data costs and unknown interventions.
method MetaCaDI is a Bayesian meta-learning framework that optimizes for rapid adaptation to new intervention targets.
result MetaCaDI significantly outperforms state-of-the-art methods in causal graph recovery and intervention target prediction.
Novel loss function improves few-shot classification performance.
problem Few-shot classification struggles with embedding space for new classes.
method Proposes self-compacting softmax loss (SSL) to prevent embedding space fullness.
result SSL leads to significant improvement in state-of-the-art performance.
PINNs can learn trivial solutions; new approach improves performance.
problem PINNs fail to learn non-trivial solutions in data-scarce settings.
method Developed an alternative sampling approach and new penalty term.
result PINNs can be improved to learn non-trivial solutions with up to 80% fewer collocation points.
Gradient-enhanced GSA uses Poincaré chaos expansions for accurate sensitivity analysis.
problem Accurately estimating Sobol' indices with limited data.
method Integrates sparse, gradient-enhanced regression with Poincaré chaos expansions for derivative-based sensitivity analysis.
result Accurately estimated Sobol' indices using limited data.
The paper improves reinforcement learning stability and efficiency with a new theoretical framework.
problem Stability and efficiency in reinforcement learning, especially in data-scarce scenarios.
method Theoretical framework using resampled U- and V-statistics to model experience replay, applied to policy evaluation and kernel ridge regression. result Significant improvements in stability and efficiency, particularly in data-scarce scenarios.
Oja's rule improves neural network training without engineered tricks.
problem Training deep neural networks with biological constraints.
method Incorporating Oja's plasticity rule into error-driven training.
result Stable, efficient learning in feedforward and recurrent architectures.
LSTM model predicts stock prices with high accuracy in stable sectors but struggles with volatile ones.
problem Predicting stock prices in emerging markets with limited data.
method Developed and evaluated an LSTM network on historical OHLCV data and technical indicators.
result Strong predictive performance (R2>0.87) for stable sectors, but challenges for volatile ones. Proposes a thermodynamic work minimization framework for guiding generative models.
problem Guiding generative models in sparse-data regimes with limited target samples or constraints.
method Regularization framework inspired by thermodynamic work, introducing Path Guidance and Observable Guidance.
result Improves sample efficiency and reduces bias in molecular simulations.
Framework improves target domain prediction using quantile matching.
problem Improving prediction accuracy in data-scarce target domains.
method Conditional quantile matching for distributional alignment.
result Empirical risk minimizer achieves tighter excess risk bound.
Tabular FMs struggle with reliable uncertainty quantification.
problem Uncertainty quantification in tabular foundation models.
method Compared TabPFN and Gaussian processes (GPs) across various regression tasks.
result GP outperforms TabPFN in data-scarce settings and when kernels are good priors.
Many real-world time-series analysis problems are characterised by scarce data. Solutions typically rely on hand-crafted features extracted from the time or frequency domain allied with classification or regression engines which condition on this (often low-dimensional) feature vector. The huge advances enjoyed by many…
In compressed sensing, a small number of linear measurements can be used to reconstruct an unknown signal. Existing approaches leverage assumptions on the structure of these signals, such as sparsity or the availability of a generative model. A domain-specific generative model can provide a stronger prior and thus allo…
Enhances random forests by smoothing predictions for better performance.
problem Suboptimal performance due to piecewise constant predictions in random forests.
method Kernel-based smoothing mechanism to introduce local regularity.
result Smoothed random forest model consistently improves predictive performance.
This work combines autoencoder transfer learning with MSCP for accurate aerodynamic predictions.
problem Data scarcity in aerodynamic modeling limits the use of high-fidelity simulations.
method Autoencoder-based transfer learning with MSCP for uncertainty-aware data fusion.
result The model achieves high accuracy with minimal high-fidelity training data and robust uncertainty bands.
Global neural networks improve financial forecasting accuracy with larger, diverse datasets.
problem Mixed empirical performance in financial time series forecasting due to local model estimation.
method Global estimation strategy that pools information across cross-sections of over 10,000 global stocks.
result Forecasting accuracy improves with larger and more heterogeneous training datasets.
This work analyzes how to choose regularization norms for adversarial training in high dimensions.
problem Choosing the right regularization norm for adversarial training in high-dimensional settings.
method Derives asymptotic descriptions and uniform convergence bounds for robust, regularized empirical risk minimizers.
result Characterizes the relationship between perturbation size and optimal regularization choice.
Spectral regularization improves learning over combinatorial spaces with limited data.
problem Learning pseudo-Boolean functions with scarce labeled data.
method Regularizing the spectral representation of learned functions using the L_1 norm.
result Regularization allows for data-frugal learning and achieves statistically optimal generalization performance.
This research improves uncertainty estimation for medical predictions, enhancing model trust and decision support.
problem Improving model uncertainty estimation for rare medical conditions.
method Developed and refined heuristics for selecting uncertainty estimation techniques, distinguishing them by clinical use-case. Also, compared ensembles vs. auto-encoders for detecting out-of-domain examples.
result Auto-encoders outperform ensembles in detecting out-of-domain examples, highlighting their importance for medical tabular data.
A new method directly encodes data into latent space using gradient flow.
problem Suboptimal representations in physical sciences due to encoder inversion.
method Decoder-only approach using gradient flow and ODEs, avoiding integrals.
result Superior data efficiency and explicit encoding compared to traditional autoencoders.
GPCDL uses Gaussian Processes to learn smooth templates from data.
problem Lack of smoothness in learned templates leads to overfitting and poor predictive performance.
method GPCDL incorporates Gaussian Process priors to enforce smoothness in the learned templates.
result GPCDL outperforms unregularized CDL in accuracy and predictive performance across various SNRs and applications.
Enhances MIL performance in scarce data scenarios using topological inductive biases.
problem Low performance of MIL in data-scarce scenarios.
method Incorporates topological inductive biases into MIL framework.
result Average performance improvements of 15.3% for synthetic datasets, 2.8% for benchmarks, and 5.5% for rare anemia classification.