CurveRL optimizes large model reasoning by reweighting prompts based on their rank and density.
problem Improving large language model reasoning through context reweighting.
method Formulated prompt reweighting as a functional derivative, proposing CurveRL based on quantile coordinate transform.
result CurveRL consistently outperforms existing methods across multiple benchmarks.
Proposes new loss functions for better handling bimodal predictive uncertainty.
problem Bimodal predictive uncertainty in machine learning models.
method Family of distribution-aware loss functions integrating normalized RMSE with Wasserstein and Cramér distances.
result Proposed loss functions reduce predictive uncertainty estimation error by 45% on complex bimodal datasets.
Deep learning algorithms can fare poorly when the training dataset suffers from heavy class-imbalance but the testing criterion requires good generalization on less frequent classes. We design two novel methods to improve performance in such scenarios. First, we propose a theoretically-principled label-distribution-awa…
A new algorithm estimates mean under varying user data sizes with local differential privacy.
problem Mean estimation with user-level local differential privacy under varying data sizes.
method Distribution-aware mean estimation algorithm for users with varying data sizes.
result Upper and lower bounds on the worst-case risk for mean estimation are derived.
A critical and challenging problem in reinforcement learning is how to learn the state-action value function from the experience replay buffer and simultaneously keep sample efficiency and faster convergence to a high quality solution. In prior works, transitions are uniformly sampled at random from the replay buffer o…
Machine learning improves financial stress testing in Indian markets.
problem Conventional stress testing limitations in Indian financial markets.
method Dimensionality reduction, latent factor modeling, Variational Autoencoders, Monte Carlo simulation.
result Improved flexibility, robustness, and realism in financial stress testing.
Discriminative learning machines often need a large set of labeled samples for training. Active learning (AL) settings assume that the learner has the freedom to ask an oracle to label its desired samples. Traditional AL algorithms heuristically choose query samples about which the current learner is uncertain. This st…
DBGAN learns graph node representations by balancing distribution consistency.
problem Graph representation learning overfits due to ignoring data distribution.
method DBGAN uses a structure-aware prior distribution and bidirectional adversarial learning.
result DBGAN achieves better trade-off between robustness and dimensionality.
Meta-learning improves with explicit modeling of task covariate distributions.
problem Ignoring the relationship between task covariates and conditional distributions limits meta-learning performance.
method Introducing a hierarchical Bayesian model that leverages samples from the marginal task covariates to better infer optimal parameters.
result Our method outperforms initialization-based meta-learning on popular classification benchmarks.
New method corrects active learning for distribution shifts and outliers.
problem Conventional active learning methods fail to account for test-time distribution.
method JEPIG, a hybrid of BALD and EPIG, maximizes expected predictive information gain.
result JEPIG outperforms conventional methods in active learning with distribution shifts.
Study on stability of GCNNs under graph perturbations.
problem Limited theoretical understanding of GCNN stability.
method Proposes a probabilistic framework to analyze GCNN stability under various graph perturbations.
result Demonstrates the importance of data distribution in stability analysis.
Paper uses SciPhyRL for optimizing large institutional portfolios.
problem Optimizing large institutional portfolios with cumulative costs and practical short horizons.
method Formulates a continuous-time optimization problem, reduces it to solving an HJB equation, and uses PINN for direct solution.
result Learned Gibbs policy yields substantial out-of-sample Sharpe ratio improvements.
Study develops ensemble machine learning framework for predicting groundwater heavy metal pollution.
problem Statistical complexity and spatial heterogeneity of heavy metal contamination in groundwater.
method Nested cross-validated ensemble machine learning with response transformations (raw, log, Gaussian copula).
result Copula-based models with DBSCAN clustering diagnostics provide the most reliable and interpretable assessments of groundwater contamination.
Single-layer GCN model improves recommendation performance with less complexity.
problem Severe computational burden and excessive model parameters in existing GCN models.
method Proposes a single-layer GCN architecture with a simplified aggregation step using DA similarity.
result Significantly outperforms existing GCN models and achieves up to a few orders of magnitude speedup.
Transfer learning improves loan recovery rate forecasting under data scarcity.
problem Data scarcity in loan portfolios limits RR modeling accuracy.
method Introduces FT-MDN-Transformer, a mixture-density tabular Transformer architecture for TL.
result FT-MDN-Transformer outperforms baseline models in RR forecasting, especially under covariate and conditional shifts.
Study analyzes Nifty 50 returns over 34 years, showing P/E ratio predicts long-term gains.
problem Understanding equity return dynamics in the Indian market over various horizons.
method Unified, distribution-aware, complexity-informed framework using 34 years of Nifty 50 data.
result P/E ratio probabilistically maps return distributions across different investment horizons.