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.
Proposes a new method to optimize graph neural network architectures on heterogeneous information networks.
MGMC method handles missing data in medical datasets for accurate disease classification.
As the availability and importance of temporal interaction data--such as email communication--increases, it becomes increasingly important to understand the underlying structure that underpins these interactions. Often these interactions form a multigraph, where we might have multiple interactions between two entities.…
The study proves planes are the only complete uniformly elliptic Weingarten multigraphs.
Classifies multigraphs for torus actions on 6D manifolds with isolated fixed points.
Fully automating machine learning pipelines is one of the key challenges of current artificial intelligence research, since practical machine learning often requires costly and time-consuming human-powered processes such as model design, algorithm development, and hyperparameter tuning. In this paper, we verify that au…
Credit assignment in Meta-reinforcement learning (Meta-RL) is still poorly understood. Existing methods either neglect credit assignment to pre-adaptation behavior or implement it naively. This leads to poor sample-efficiency during meta-training as well as ineffective task identification strategies. This paper provide…
Neural Architecture Search (NAS) has been quite successful in constructing state-of-the-art models on a variety of tasks. Unfortunately, the computational cost can make it difficult to scale. In this paper, we make the first attempt to study Meta Architecture Search which aims at learning a task-agnostic representation…
Meta-learning balances task-specific modeling and optimization complexity.
Beam search is widely used for approximate decoding in structured prediction problems. Models often use a beam at test time but ignore its existence at train time, and therefore do not explicitly learn how to use the beam. We develop an unifying meta-algorithm for learning beam search policies using imitation learning.…
Meta learning optimizes neural network quantization for efficient inference.
A typical census of 3-manifolds contains all manifolds (under various constraints) that can be triangulated with at most n tetrahedra. Al- though censuses are useful resources for mathematicians, constructing them is difficult: the best algorithms to date have not gone beyond n = 12. The underlying algorithms essential…
There is no free lunch, no single learning algorithm that will outperform other algorithms on all data. In practice different approaches are tried and the best algorithm selected. An alternative solution is to build new algorithms on demand by creating a framework that accommodates many algorithms. The best combination…
Neural architecture search has recently attracted lots of research efforts as it promises to automate the manual design of neural networks. However, it requires a large amount of computing resources and in order to alleviate this, a performance prediction network has been recently proposed that enables efficient archit…
LLMs learn to recommend models and hyperparameters from dataset metadata.
Hyperparameter optimization aims to find the optimal hyperparameter configuration of a machine learning model, which provides the best performance on a validation dataset. Manual search usually leads to get stuck in a local hyperparameter configuration, and heavily depends on human intuition and experience. A simple al…
Study circle actions on unitary manifolds with discrete fixed points.
Self-referential meta learning avoids explicit optimization by modifying itself.
Meta-graph is currently the most powerful tool for similarity search on heterogeneous information networks,where a meta-graph is a composition of meta-paths that captures the complex structural information. However, current relevance computing based on meta-graph only considers the complex structural information, but i…
In this paper, we study a circle action on a compact oriented manifold with a discrete fixed point set. The fixed point data consists of the weights of the -representations at the fixed points. We prove various results and properties of the action, in terms of the fixed point data. We show that the manifold can be…
Survey of techniques for automating hyperparameter optimization in machine learning.
This paper uses XAI techniques to explain meta-learning models.
LA-MCTS learns search space partition for black-box optimization using Monte Carlo Tree Search.
This supplementary material aims to describe the proposed multi-label classification (MLC) search spaces based on the MEKA and WEKA softwares. First, we overview 26 MLC algorithms and meta-algorithms in MEKA, presenting their main characteristics, such as hyper-parameters, dependencies and constraints. Second, we revie…
In this short paper we investigate whether meta-learning techniques can be used to more effectively tune the hyperparameters of machine learning models using successive halving (SH). We propose a novel variant of the SH algorithm (MeSH), that uses meta-regressors to determine which candidate configurations should be el…
Meta-Semi learns to optimize SSL with minimal hyper-parameter tuning.
Spectral Graph Convolutional Networks (GCNs) are a generalization of convolutional networks to learning on graph-structured data. Applications of spectral GCNs have been successful, but limited to a few problems where the graph is fixed, such as shape correspondence and node classification. In this work, we address thi…
Reinforcement learning (RL) algorithms have demonstrated promising results on complex tasks, yet often require impractical numbers of samples since they learn from scratch. Meta-RL aims to address this challenge by leveraging experience from previous tasks so as to more quickly solve new tasks. However, in practice, th…
Meta-learning priors improves safe Bayesian optimization.
MAML optimizes shared priors for subtasks in a nonconvex meta-objective.
To solve a machine learning problem, one typically needs to perform data preprocessing, modeling, and hyperparameter tuning, which is known as model selection and hyperparameter optimization.The goal of automated machine learning (AutoML) is to design methods that can automatically perform model selection and hyperpara…
Novel method for high-dimensional BO using CMA to define local regions.
We study the problem of end-to-end learning from complex multigraphs with potentially very large numbers of edges between two vertices, each edge labeled with rich information. Examples range from communication networks to flights between airports or financial transaction graphs. We propose Latent-Graph Convolutional N…
Unified RL meta-learning framework for few-shot optimization.
The design of neural network architectures is an important component for achieving state-of-the-art performance with machine learning systems across a broad array of tasks. Much work has endeavored to design and build architectures automatically through clever construction of a search space paired with simple learning …
The recent progress in neural architecture search (NAS) has allowed scaling the automated design of neural architectures to real-world domains, such as object detection and semantic segmentation. However, one prerequisite for the application of NAS are large amounts of labeled data and compute resources. This renders i…
AEGiS optimizes expensive function evaluations asynchronously.
L2O-CFGD meta-learns hyperparameters for FGD, improving performance.
The field of few-shot learning has recently seen substantial advancements. Most of these advancements came from casting few-shot learning as a meta-learning problem. Model Agnostic Meta Learning or MAML is currently one of the best approaches for few-shot learning via meta-learning. MAML is simple, elegant and very pow…
New models capture heterogeneous network density, improving community detection.
Meta-learning curiosity algorithms improves exploration across various tasks.
A new distance for mixed-variable, hierarchical datasets with meta variables.
Neural Architecture Search remains a very challenging meta-learning problem. Several recent techniques based on parameter-sharing idea have focused on reducing the NAS running time by leveraging proxy models, leading to architectures with competitive performance compared to those with hand-crafted designs. In this pape…
Autodock is a widely used molecular modeling tool which predicts how small molecules bind to a receptor of known 3D structure. The current version of AutoDock uses meta-heuristic algorithms in combination with local search methods for doing the conformation search. Appropriate settings of hyperparameters in these algor…
Evolutionary Strategies optimize hyper-parameters for off-policy learning.
In this paper, we present a novel way to summarize the structure of large graphs, based on non-parametric estimation of edge density in directed multigraphs. Following coclustering approach, we use a clustering of the vertices, with a piecewise constant estimation of the density of the edges across the clusters, and ad…
This paper introduces a new system for discovering patterns in morphogenetic systems using modular architecture and unsupervised learning.
A new optimizer, MVO, improves nonlinear regression performance.