On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

12 results for “DRMs”

Logical Explanations for Deep Relational Machines Using Relevance Informationcs.LG

The paper explains deep neural network predictions using logical proxies.

problem Creating understandable explanations for deep neural network predictions.

method Randomized propositionalization and Bayes-like approach to identify logical proxies.

result Models in first-order logic can approximate DRM's predictions in local regions.

Deep Neural Networks Logical Explanations Bayes Approach Relevance Information DRMs

2018-07-02abs ↗pdf ↗

Discriminative Ridge Machine: A Classifier for High-Dimensional Data or Imbalanced Datacs.LG

A new DRM classifier for high-dimensional and imbalanced data.

problem Classification in high-dimensional and imbalanced data.

method Discriminative regression approach with iterative algorithms.

result Superior performance compared to state-of-the-art classifiers.

classification high-dimensional data imbalanced data discriminative regression iterative algorithms

2019-04-16abs ↗pdf ↗

Unveiling the Potential of Robustness in Selecting Conditional Average Treatment Effect Estimatorscs.LG

Paper introduces DRM for selecting robust CATE estimators.

problem Selecting CATE estimators without counterfactual outcomes.

method Distributionally Robust Metric (DRM) for CATE estimator selection.

result DRM selects robust CATE estimators robust to distribution shift.

CATE DRM Robustness Metric Nuisance-Free

2024-02-28abs ↗pdf ↗

A Semiparametric Approach to Causal Inferencestat.ME

The paper introduces a DRM for causal inference, offering a flexible method to analyze counterfactual distributions.

problem Estimating mean causal effects is limited; a distributional perspective is needed for a more thorough understanding.

method The paper employs a semiparametric density ratio model (DRM) with an empirical likelihood (EL) approach to estimate counterfactual distribution functions.

result The DRM framework enables direct and transparent causal inference from a distributional perspective, validated by numerical studies.

causal inference semiparametric model density ratio model empirical likelihood counterfactual distributions

2024-11-01abs ↗pdf ↗

Risk-Averse Markov Decision Processes through a Distributional Lensmath.OC

Risk measures applied to dynamic Markov processes with varying risk aversion.

problem Investigating dynamic risk measures in Markov decision processes with varying risk aversion.

method Distributional viewpoint on law-invariant convex risk measures, applied to Markov decision processes with latent costs and random actions.

result Existence of optimal policies in finite and infinite time horizons under mild assumptions.

risk measures Markov decision processes dynamic programming risk aversion convex risk measures

2022-03-17abs ↗pdf ↗

A Priori Generalization Analysis of the Deep Ritz Method for Solving High Dimensional Elliptic Equationsmath.NA

Paper analyzes DRM for solving high-dimensional elliptic PDEs with generalization bounds.

problem Analyzing generalization error of neural network methods for high-dimensional PDEs.

method Developed a new solution theory for spectral Barron space and derived generalization error bounds.

result Generalization error bounds are independent of dimension and solutions lie in spectral Barron space.

Deep Ritz Method Generalization Error Neural Networks Elliptic PDEs Spectral Barron Space

2021-01-05abs ↗pdf ↗

Unified Perspective on Probability Divergence via Maximum Likelihood Density Ratio Estimation: Bridging KL-Divergence and Integral Probability Metricscs.LG

Unified view of KL-divergence and IPMs via DRE, with new DRM metrics.

problem Unified understanding of KL-divergence and IPMs.

method Unified representation via maximum likelihood density-ratio estimation (DRE).

result Unified form of IPMs and novel DRM metrics.

KL-divergence IPMs Density Ratio Estimation Maximum Likelihood Density Ratio Metrics

2022-01-31abs ↗pdf ↗

Sobolev Acceleration and Statistical Optimality for Learning Elliptic Equations via Gradient Descentmath.NA

Gradient descent achieves optimal learning for elliptic PDEs via Sobolev norms.

problem Learning elliptic PDEs from noisy data.

method Gradient descent on Sobolev norm objective functions.

result Gradient descent achieves statistical optimality for elliptic PDEs.

Sobolev norms gradient descent elliptic PDEs statistical optimality kernel regression

2022-05-15abs ↗pdf ↗

Machine Learning For Elliptic PDEs: Fast Rate Generalization Bound, Neural Scaling Law and Minimax Optimalitymath.NA

Paper studies deep learning for solving elliptic PDEs, proving optimal bounds and neural scaling laws.

problem Solving elliptic PDEs from random samples using machine learning.

method Deep Ritz Method and Physics-Informed Neural Networks (PINNs) for the Schrödinger equation.

result Proves minimax optimal bounds and neural scaling laws for deep PDE solvers.

Machine Learning Elliptic PDEs Deep Ritz Method Physics-Informed Neural Networks Schrödinger Equation

2021-10-13abs ↗pdf ↗

Efficient Reinforcement Learning in Probabilistic Reward Machinesstat.ML

Efficient RL in PRMs with improved regret bound.

problem Reinforcement learning in probabilistic reward machines with non-Markovian rewards.

method Design of an algorithm with a new regret bound of

\widetilde{O}(\sqrt{HOAT} + H^2O^2A^{3/2} + H\sqrt{T})

result Improved regret bound over existing methods, matching lower bound up to a logarithmic factor.

Reinforcement Learning Probabilistic Reward Machines Non-Markovian Rewards Regret Bound Simulation Lemma

2024-08-19abs ↗pdf ↗

Supersolutionshep-th

We develop classical globally supersymmetric theories. As much as possible, we treat various dimensions and various amounts of supersymmetry in a uniform manner. We discuss theories both in components and in superspace. Throughout we emphasize geometric aspects. The beginning chapters give a general discussion about su…

1999-01-20abs ↗pdf ↗

Error Analysis of Three-Layer Neural Network Trained with PGD for Deep Ritz Methodmath.NA

Study analyzes error in neural network solving PDEs, providing convergence and error bounds.

problem Error analysis of neural network solving PDEs.

method Three-layer tanh neural network with projected gradient descent (PGD).

result Comprehensive error analysis including approximation, generalization, and optimization errors.

error analysis neural networks partial differential equations deep Ritz method projected gradient descent

2024-05-19abs ↗pdf ↗