BIOMRC dataset improves MRC performance, especially for non-experts.
problem Improving machine reading comprehension in biomedical texts.
method Developed a new dataset and tested two neural models, along with a BERT-based model.
result BERT-based model outperforms all other methods and reaches expert-level accuracy.
MRCs minimize worst-case expected 0-1 loss and provide performance guarantees.
problem Minimizing expected 0-1 loss in classification.
method Minimizes worst-case expected 0-1 loss over uncertainty sets defined by linear constraints.
result Achieves efficient learning and generalization with performance guarantees.
Paper develops MRCs for supervised classification using generalized maximum entropy.
problem Developing robust classifiers for decision problems.
method Generalized maximum entropy principle applied to minimax risk classifiers.
result Learning techniques for determining MRCs with performance guarantees.
MRC-LSTM predicts Bitcoin prices using CNN and LSTM.
problem Predicting Bitcoin price with high volatility and complex factors.
method Combines MRC and LSTM, focusing on multi-scale features and long-term dependencies.
result MRC-LSTM significantly outperforms other models in Bitcoin price prediction.
Paper introduces MRCs that minimize worst-case 0-1 loss, providing tight performance guarantees.
problem Minimizing worst-case 0-1 loss in classification.
method MRCs that minimize worst-case 0-1 loss with uncertainty sets of distributions.
result MRCs provide tight performance guarantees and are strongly universally consistent.
Existing machine reading comprehension (MRC) models do not scale effectively to real-world applications like web-level information retrieval and question answering (QA). We argue that this stems from the nature of MRC datasets: most of these are static environments wherein the supporting documents and all necessary inf…
MRC improves credit assignment in multi-agent LLM systems, achieving high returns and transparency.
problem Lack of principled credit assignment in multi-agent LLM decision systems, vulnerability to regime shifts, and limited transparency.
method Market Regime Council (MRC) computes exact Shapley credits, uses exponentially weighted performance histories, Bayesian adaptive mixture, and regime-dependent multipliers.
result MRC achieves a Sharpe ratio of 1.51 and a cumulative return of 440.1% over 1,037 trading days, ranking first on CR, SR, and IR.
Two remarks on curvature properties of Kähler manifolds.
problem Curvature properties of Kähler manifolds.
method Analyzing semi-positive holomorphic sectional curvature and quasi-negative k-Ricci curvature. result For semi-positive holomorphic sectional curvature, the rational dimension of the MRC fibration equals the number of non-truly-flat directions. For quasi-negative k-Ricci curvature, the canonical bundle is ample. Machine Reading Comprehension (MRC) is an important topic in the domain of automated question answering and in natural language processing more generally. Since the release of the SQuAD 1.1 and SQuAD 2 datasets, progress in the field has been particularly significant, with current state-of-the-art models now exhibiting…
Adding an unknot to any link equals its bridge number and meridional rank.
problem Proving the Meridional Rank Conjecture for any link.
method Embedding an unknot in a link's complement to achieve the conjecture and proving it for new families of links.
result Bridge numbers and meridional ranks are equal for any link and its unknot.
MRCpy implements minimax risk classifiers with performance guarantees and distribution shift adaptability.
problem Classical risk minimization approaches are not robust to distribution shifts.
method Robust risk minimization approach for minimax risk classifiers.
result MRCs provide performance guarantees and adapt to distribution shifts.
Paper presents an efficient algorithm for learning minimax risk classifiers with large-scale data.
problem Efficient learning of minimax risk classifiers for large-scale data with multiple classes.
method Combination of constraint and column generation for efficient learning.
result 10x speedup for general large-scale data and 100x speedup with many classes.
Quantum reservoir computing needs coherence influx for effective information processing.
problem Understanding and optimizing quantum reservoir computing.
method Theoretical and numerical analysis of quantum systems, focusing on coherence influx and spectral radius of Pauli transfer matrix.
result Coherence influx is essential for realizing nonstationary echo state property in quantum reservoir computing.
The paper studies foliations on smooth projective varieties and their properties.
problem Characterizing and understanding foliations on smooth projective varieties.
method Develops a structure theorem for smooth projective varieties with almost nef regular foliations, using a smooth morphism and MRC fibration.
result An almost nef regular foliation on a smooth projective variety can be decomposed into a numerically flat regular foliation and a smooth morphism.
The study of projective varieties with nef anticanonical divisors and log terminal singularities.
problem Understanding the structure and properties of projective varieties with specific divisor conditions.
method Analyzing the Albanese map and MRC fibration for klt projective varieties, showing locally constant fibrations and product decompositions.
result Generalization of results for smooth projective varieties to the klt case, including decomposition into rationally connected and projective varieties with trivial canonical divisor.
In this paper, we pose several conjectures on structures and images of maximal rationally connected fibrations of smooth projective varieties admitting semi-positive holomorphic sectional curvature. Toward these conjectures, we prove that the canonical bundle of images of such fibrations is not big. Our proof gives a g…
The paper extends structure theorem to projective klt varieties with specific tangent sheaf properties.
problem Understanding the structure of projective klt varieties with nef tangent sheaves.
method Developing theory of positivity of coherent sheaves and proving structure theorem.
result Projective klt varieties with specific tangent sheaf properties admit rationally connected fibrations onto abelian varieties.
In a previous paper, we proved that a projective Kähler manifold of positive total scalar curvature is uniruled. At the other end of the spectrum, it is a well-known theorem of Campana and Kollár-Miyaoka-Mori that a projective Kähler manifold of positive Ricci curvature is rationally connected. In the present work, we …
Simulation-based inference aids in predicting disease dynamics for health policy.
problem Predicting disease dynamics to inform public health interventions.
method Simulation-based inference using machine learning.
result Potential for efficient interpretable Bayesian inference in epidemiological models.
Efficient learning of minimax risk classifiers in high dimensions.
problem Efficient learning of classifiers in high-dimensional data.
method Iterative algorithm leveraging constraint generation methods for minimax risk classifiers.
result The algorithm provides efficient learning and feature selection in high-dimensional scenarios.
The paper studies Kähler manifolds with partially semi-positive curvature and rational connectedness.
problem Analyzing compact Kähler manifolds with partially semi-positive curvature and rational connectedness.
method Proving rational connectedness for manifolds with BC-p positive tangent bundles, and applying these results to curvature conditions. result Confirming a conjecture and generalizing results on rational connectedness and curvature conditions.
Proposes a new method to adapt to covariate shifts in supervised learning.
problem Covariate shift in training and testing samples with different marginal distributions.
method Minimax risk classification (MRC) approach that weights both training and testing samples.
result Significantly enhanced classification performance in synthetic and empirical experiments.