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.
SPoC uses search to translate pseudocode into correct programs with error localization.
DeepEvolution improves testing of deep neural networks by generating diverse test cases.
Neurally-Guided Structure Inference combines search and data-driven methods for efficient, robust structure inference.
PackIt creates a virtual space for testing geometric planning skills.
New sparse GP model learns compositional kernels efficiently.
BPI models 2D patterns on multiple planes and 3D scene from a single image.
Neural A* uses machine learning to improve path planning efficiency.
SIM models user interests from long sequential behavior data, improving click-through rate prediction.
This paper presents preliminary work on learning the search heuristic for the optimal motion planning for automated driving in urban traffic. Previous work considered search-based optimal motion planning framework (SBOMP) that utilized numerical or model-based heuristics that did not consider dynamic obstacles. Optimal…
Neural model with parameterized algorithms improves graph CO problem solving.
Search-based methods for hard combinatorial optimization are often guided by heuristics. Tuning heuristics in various conditions and situations is often time-consuming. In this paper, we propose NeuRewriter that learns a policy to pick heuristics and rewrite the local components of the current solution to iteratively i…
Addressing the issue of SVMs parameters optimization, this study proposes an efficient memetic algorithm based on Particle Swarm Optimization algorithm (PSO) and Pattern Search (PS). In the proposed memetic algorithm, PSO is responsible for exploration of the search space and the detection of the potential regions with…
Accurate real-time tracking of influenza outbreaks helps public health officials make timely and meaningful decisions that could save lives. We propose an influenza tracking model, ARGO (AutoRegression with GOogle search data), that uses publicly available online search data. In addition to having a rigorous statistica…
We propose a neural information processing system which is obtained by re-purposing the function of a biological neural circuit model, to govern simulated and real-world control tasks. Inspired by the structure of the nervous system of the soil-worm, C. elegans, we introduce Neuronal Circuit Policies (NCPs), defined as…
Paper trains models to resist string transformations.
XNAS optimizes neural architecture search using expert advice theory.
The classification of MRI images according to the anatomical field of view is a necessary task to solve when faced with the increasing quantity of medical images. In parallel, advances in deep learning makes it a suitable tool for computer vision problems. Using a common architecture (such as AlexNet) provides quite go…
The performance of Feedforward neural network (FNN) fully de-pends upon the selection of architecture and training algorithm. FNN architecture can be tweaked using several parameters, such as the number of hidden layers, number of hidden neurons at each hidden layer and number of connections between layers. There may b…
Statistical relational frameworks such as Markov logic networks and probabilistic soft logic (PSL) encode model structure with weighted first-order logical clauses. Learning these clauses from data is referred to as structure learning. Structure learning alleviates the manual cost of specifying models. However, this be…
We consider the problem of sparse phase retrieval from Fourier transform magnitudes to recover the -sparse signal vector and its support . We exploit extended support estimate with size larger than satisfying and obtained by a trained deep neural net…
INT benchmark tests theorem proving agents' ability to generalize to unseen theorems.
Efficiently reduces computational burden of rollout acquisition functions in Bayesian optimization.
ISMCTS-BR learns best responses in large games, approximating worst-case performance.
How can we efficiently gather information to optimize an unknown function, when presented with multiple, mutually dependent information sources with different costs? For example, when optimizing a robotic system, intelligently trading off computer simulations and real robot testings can lead to significant savings. Exi…
P3I learns holistic scene representations from a single image.
Dimension reduction and variable selection are performed routinely in case-control studies, but the literature on the theoretical aspects of the resulting estimates is scarce. We bring our contribution to this literature by studying estimators obtained via L1 penalized likelihood optimization. We show that the optimize…
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…
AutoAlpha efficiently discovers effective alpha factors for quantitative investment.
Yau's Affine Normal Descent optimizes smooth unconstrained problems with geometrically adapted directions.
Wireless systems perform rate adaptation to transmit at highest possible instantaneous rates. Rate adaptation has been increasingly granular over generations of wireless systems. The base-station uses SINR and packet decode feedback called acknowledgement/no acknowledgement (ACK/NACK) to perform rate adaptation. SINR i…
Approximate inference in high-dimensional, discrete probabilistic models is a central problem in computational statistics and machine learning. This paper describes discrete particle variational inference (DPVI), a new approach that combines key strengths of Monte Carlo, variational and search-based techniques. DPVI is…
In many sequential decision making tasks, it is challenging to design reward functions that help an RL agent efficiently learn behavior that is considered good by the agent designer. A number of different formulations of the reward-design problem, or close variants thereof, have been proposed in the literature. In this…
Enzyme sequences and structures are routinely used in the biological sciences as queries to search for functionally related enzymes in online databases. To this end, one usually departs from some notion of similarity, comparing two enzymes by looking for correspondences in their sequences, structures or surfaces. For a…
Paper proposes a new model and methods for robustly de-interleaving HMP mixtures.
New test assesses reliability of auto-generated features.
RSO uses random weight perturbations to train deep networks without gradients.
Algorithm provides fair clustering guarantees for k-means and k-median.
Causal effect identification considers whether an interventional probability distribution can be uniquely determined without parametric assumptions from measured source distributions and structural knowledge on the generating system. While complete graphical criteria and procedures exist for many identification problem…
Paper presents a self-supervised method to infer road lane networks.
Transformers learn to predict chess moves with surprising accuracy and strength.
In many settings, a decision-maker wishes to learn a rule, or policy, that maps from observable characteristics of an individual to an action. Examples include selecting offers, prices, advertisements, or emails to send to consumers, as well as the problem of determining which medication to prescribe to a patient. Whil…
UNAS combines DNAS and RL for efficient architecture search.
Paper tackles sparse recovery with shuffled labels, establishing statistical and computational limits.
This paper improves neural architecture search by focusing on novelty-driven sampling.
Two approaches scale up DNN optimization for diverse edge devices.
BOOOM optimizes orthonormal matrices without needing gradients.
A framework for efficient multi-objective optimization using entropy search.
New method solves stochastic optimization problems with random models.