Research
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.

169,341 papers · 148 categories

Trend · papers per month

201403604805 · Jun 202019922001200920182026
48 results for modularity optimization

LaMBO optimizes modular systems with switching costs, achieving better results than existing methods.

problem Optimizing systems with costly variable updates in a sequence of modules.
method Lazy Modular Bayesian Optimization (LaMBO) that minimizes switching costs.
result LaMBO achieves vanishing regret and improves over existing cost-aware Bayesian optimization algorithms.

Soft modularization improves sample efficiency and performance in reinforcement learning.

problem Challenges in training multiple tasks jointly in reinforcement learning.
method Explicit modularization technique on policy representation, soft modularization method.
result Improves sample efficiency and performance over strong baselines in robotics manipulation tasks.

The paper develops a new approach to conditional risk measures using modular convex analysis.

problem Developing a new method for conditional risk measures.
method Random modular approach to conditional certainty equivalents and niveloids in the conditional LL^{\infty}-space.
result Retrieves a conditional variational formula for optimized certainty equivalents and applies it to the conditional entropic risk measure.

We simplify modularity optimization using a Ginzburg-Landau functional and an MBO scheme.

problem Modularity optimization in network communities.
method We derive a Ginzburg-Landau functional approximation and an MBO scheme for modularity optimization.
result Our method converges to the correct energy in the limit and is faster and more stable.

New framework for modular reinforcement learning reduces sample complexity.

problem Achieving independent credit assignment in reinforcement learning.
method Defining modular credit assignment as minimizing algorithmic mutual information, introducing modularity criterion for causal analysis.
result Single-step temporal difference action-value methods meet the modularity criterion, improving sample efficiency.

The study examines if ReLU activation function is optimal for modularity in neural networks.

problem Finding the best activation function for modularity in neural networks.
method Comparing ReLU with other activation functions for modularity and performance.
result ReLU may not be the best choice for modularity, suggesting other functions could be more suitable.

Enhances multi-modular models by directing information flow between components.

problem Improving predictive performance in multi-modular models with misspecification.
method Introduces Semi-Modular Inference (SMI) with an influence parameter to control information flow between modules.
result SMI allows for tunable and directed information flow, improving prediction in some settings.

Metareasoning optimizes modular systems by dynamically adjusting configurations.

problem Maximizing system utility in high-stakes tasks with modular subsystems.
method Employing reinforcement learning with rich contextual representations to dynamically adjust module configurations.
result Significant improvement in system performance across various reinforcement learning techniques.

Study on AI-driven modeling for high burnup accident-tolerant fuels in SMRs.

problem Design and optimization of high burnup accident-tolerant fuels for SMRs.
method Artificial intelligence and multi-scale modeling (neutronics, thermal hydraulics, fuel performance).
result Demonstrated the effectiveness of AI in modeling and optimizing SMR fuels.

Recursive Feature Machines show grokking in modular arithmetic without neural networks.

problem Grokking in modular arithmetic tasks.
method Recursive Feature Machines (RFM) with Average Gradient Outer Product (AGOP).
result RFM and neural networks learn block-circulant features to solve modular arithmetic.

We present a novel clustering approach for moving object trajectories that are constrained by an underlying road network. The approach builds a similarity graph based on these trajectories then uses modularity-optimization hiearchical graph clustering to regroup trajectories with similar profiles. Our experimental stud…

2012-05-10abs ↗pdf ↗

Modularity-aware GAE and VGAE improve community detection and link prediction.

problem Improving community detection with GAE and VGAE in the absence of node features.
method Introducing a modularity-aware message passing scheme and regularizer to GAE and VGAE encoders.
result Jointly addressing community detection and link prediction with high accuracy is possible.

Greedy algorithms near-optimal for adaptive optimization with budget constraint.

problem Adaptive optimization with budget constraint in AI and ML.
method Investigates two simple greedy algorithms and a combined algorithm for pointwise submodular and cost-sensitive submodular functions.
result Best greedy algorithm is near-optimal with respect to optimal algorithm using half the budget.

SDQL uses modular deep Q networks to efficiently learn multi-stage optimal control tasks.

problem Training complex deep reinforcement learning models for multi-stage control tasks is inefficient and unstable.
method Stacked Deep Q Learning (SDQL) with modular Q networks and backward training.
result SDQL efficiently learns optimal control policies for multi-stage tasks with high-dimensional state and action spaces.

Researchers found the global topology of the Eisenstein-Picard modular surface.

problem Understanding the global topology of the Eisenstein-Picard modular surface.
method Quotient space of the complex hyperbolic plane by the modular group.
result Determined the global topology of the Eisenstein-Picard modular surface as a 4-orbifold.

Sine activation functions enable two-layer neural networks to learn modular addition more efficiently.

problem Learning modular addition with two-layer neural networks.
method Introduced and analyzed sine activation functions, providing theoretical and empirical evidence.
result Sine activation functions allow for constant-width network realizations of modular addition, whereas ReLU networks require linear width scaling.

A new method for fast structure learning with modular regularization.

problem Estimating graphical model structure from high-dimensional and undersampled data.
method A novel method leveraging information-theoretic measures and structured latent factor models to derive an optimization objective encouraging modular structures.
result The proposed method recovers modular structure better as the dimensionality increases and outperforms state-of-the-art estimators at a fraction of the computational cost.

Study modular surfaces in Lorentz-Minkowski 3-space, classifying and analyzing their curvature and applications.

problem Understanding the curvature properties of modular surfaces in Lorentz-Minkowski space.
method Analyzing the sign of Gaussian and mean curvature, classifying surfaces, and applying to conformal field theories.
result Complete classification of zero Gaussian curvature modular surfaces and non-existence of non-planar maximal modular surfaces.

Modular neural networks generalize better with less data.

problem Theoretical and practical understanding of how modularity improves neural network generalization.
method Theoretical analysis of sample complexity, development of a novel learning rule.
result Modular networks require fewer samples to generalize compared to nonmodular networks, especially in high-dimensional tasks.

The paper computes presentations of cluster modular groups and verifies their generation by Dehn twists.

problem Computing presentations and verifying generation of cluster modular groups.
method A method to compute presentations of saturated cluster modular groups and verification of generation by cluster Dehn twists.
result The cluster modular groups of specified types are virtually generated by cluster Dehn twists.

Convexified modularity maximization for degree-corrected SBMs improves community detection.

problem Stochastic block models assume equal node degrees, but real-world networks often have degree heterogeneity.
method Convex programming relaxation of modularity maximization, followed by a 1 \ell_1 -norm k k -median procedure.
result The method provides theoretical guarantees for clustering accuracy, even in sparse networks.

Our aim is to introduce and advocate non-ΣΣ (non-symmetric) modular operads. While ordinary modular operads were inspired by the structure of the moduli space of stable complex curves, non-ΣΣ modular operads model surfaces with open strings outputs. An immediate application of our theory is a short proof that the mod…

2014-10-13abs ↗pdf ↗

Neural networks learn modular arithmetic but not all, extending known solutions to generalize.

problem Neural networks struggle with modular arithmetic, especially for polynomials.
method Developed analytical solutions for MLP networks to learn modular addition and multiplication, then combined these solutions to generalize on arbitrary modular polynomials.
result Neural networks can learn and generalize solutions to modular polynomials, supporting the hypothesis that some polynomials are learnable.

Fuchsian groups with a modular embedding have the richest arithmetic properties among non-arithmetic Fuchsian groups. But they are very rare, all known examples being related either to triangle groups or to Teichmueller curves. In Part I of this paper we study the arithmetic properties of the modular embedding and deve…

2015-03-19abs ↗pdf ↗

mlr3mbo is a modular R toolbox for Bayesian optimization.

problem Efficiently solving optimization problems with multiple objectives and constraints.
method Bayesian optimization with support for multi-objective, multi-point proposals, parallelization, and custom algorithms.
result mlr3mbo performs competitively with state-of-the-art optimizers and robustly handles various optimization regimes.

ResMixNet models learn invariant relational reasoning tasks with fewer parameters.

problem Learning invariant relational reasoning tasks in images with random transformations.
method Introduced Residual Mixture Network (ResMixNet) with a mixture-of-experts architecture.
result ResMixNet models achieve less than 2% test error on MNIST Parity task and less than 1% on colorized Pentomino task.