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.
NeuroFabric proposes a method to optimize sparse network training topologies.
We introduce DeepInversion, a new method for synthesizing images from the image distribution used to train a deep neural network. We 'invert' a trained network (teacher) to synthesize class-conditional input images starting from random noise, without using any additional information about the training dataset. Keeping …
DAD++ improves test-time adversarial defense without access to training data.
Unified framework for data-free sampling using Wasserstein gradient flows.
Framework reuses pre-trained models for data-free transfer learning.
Efficiently distills pretrained text-to-image models without real data, improving FID and CLIP scores.
We propose a parallel-data-free voice-conversion (VC) method that can learn a mapping from source to target speech without relying on parallel data. The proposed method is general purpose, high quality, and parallel-data free and works without any extra data, modules, or alignment procedure. It also avoids over-smoothi…
Knowledge Distillation (KD) has made remarkable progress in the last few years and become a popular paradigm for model compression and knowledge transfer. However, almost all existing KD algorithms are data-driven, i.e., relying on a large amount of original training data or alternative data, which is usually unavailab…
SiD distills pretrained diffusion models into a fast one-step generator.
MAZE attacks a model without data, using synthetic inputs.
Paper detects Trojan neural networks with limited or no data.
Recently, an extensive amount of research has been focused on compressing and accelerating Deep Neural Networks (DNN). So far, high compression rate algorithms require part of the training dataset for a low precision calibration, or a fine-tuning process. However, this requirement is unacceptable when the data is unava…
A new reinforcement learning method improves Max-Cut solutions without needing training data.
This note considers softmax parameter estimation when little/no labeled training data is available, but a priori information about the relative geometry of class label log-odds boundaries is available. It is shown that `data-free' softmax model synthesis corresponds to solving a linear system of parameter equations, wh…
We introduce a data-free quantization method for deep neural networks that does not require fine-tuning or hyperparameter selection. It achieves near-original model performance on common computer vision architectures and tasks. 8-bit fixed-point quantization is essential for efficient inference on modern deep learning …
Tree-Query uses LLMs to discover causal relationships in a transparent, interpretable manner.
Learning portable neural networks is very essential for computer vision for the purpose that pre-trained heavy deep models can be well applied on edge devices such as mobile phones and micro sensors. Most existing deep neural network compression and speed-up methods are very effective for training compact deep models, …
Physics-informed neural operator learns from coarse to fine discretized data.
New framework trains large SciML models solving PDEs in reasonable time.
Paper introduces a simulator-free approach to reinforcement learning policy distillation.
This text is the rejoinder following the discussion of a survey paper about minimal penalties and the slope heuristics (Arlot, 2019. Minimal penalties and the slope heuristics: a survey. Journal de la SFDS). While commenting on the remarks made by the discussants, it provides two new results about the slope heuristics …
Proposes a method to imitate active learning heuristics for better performance.
This research evaluates and introduces new heuristics for clustering Bitcoin blockchain entities.
New method uses diffusion models for unsupervised combinatorial optimization.
Link prediction is a key problem for network-structured data. Link prediction heuristics use some score functions, such as common neighbors and Katz index, to measure the likelihood of links. They have obtained wide practical uses due to their simplicity, interpretability, and for some of them, scalability. However, ev…
Nemo improves WS learning pipeline by 20%.
This paper evaluates heuristics and hyperparameters in weight-sharing NAS methods.
Interactive weak supervision learns useful heuristics from user feedback.
We propose a general approach to modeling semi-supervised learning (SSL) algorithms. Specifically, we present a declarative language for modeling both traditional supervised classification tasks and many SSL heuristics, including both well-known heuristics such as co-training and novel domain-specific heuristics. In ad…
We implement a market microstructure model including informed, uninformed and heuristic-driven investors, which latter behave in line with loss-aversion and mental accounting. We show that the probability of informed trading (PIN) varies significantly during 2008. In contrast, the probability of heuristic-driven tradin…
The report evaluates heuristics for learning timescale graphical event models.
New heuristics for predicting links in multiplex networks.
Recently two search algorithms, A* and breadth-first branch and bound (BFBnB), were developed based on a simple admissible heuristic for learning Bayesian network structures that optimize a scoring function. The heuristic represents a relaxation of the learning problem such that each variable chooses optimal parents in…
Finding the optimal -means clustering is NP-hard in general and many heuristics have been designed for minimizing monotonically the -means objective. We first show how to extend Lloyd's batched relocation heuristic and Hartigan's single-point relocation heuristic to take into account empty-cluster and single-poin…
Heuristic algorithms such as simulated annealing, Concorde, and METIS are effective and widely used approaches to find solutions to combinatorial optimization problems. However, they are limited by the high sample complexity required to reach a reasonable solution from a cold-start. In this paper, we introduce a novel …
Bayesian symbolic regression automates model discovery from data.
This work explores the non-convex optimization in compressive learning and the performance of heuristics.
In kernel methods, the median heuristic has been widely used as a way of setting the bandwidth of RBF kernels. While its empirical performances make it a safe choice under many circumstances, there is little theoretical understanding of why this is the case. Our aim in this paper is to advance our understanding of the …
Heuristic weighting improves denoising score matching without requiring noise distribution assumptions.
We propose a technique for declaratively specifying strategies for semi-supervised learning (SSL). The proposed method can be used to specify ensembles of semi-supervised learning, as well as agreement constraints and entropic regularization constraints between these learners, and can be used to model both well-known h…
Two heuristics solve dynamic multiple travelling salesmen problems.
A* is a popular path-finding algorithm, but it can only be applied to those domains where a good heuristic function is known. Inspired by recent methods combining Deep Neural Networks (DNNs) and trees, this study demonstrates how to train a heuristic represented by a DNN and combine it with A*. This new algorithm which…
Deep RL learns 2-opt heuristics to improve TSP solutions.
Singing voice conversion is a task to convert a song sang by a source singer to the voice of a target singer. In this paper, we propose using a parallel data free, many-to-one voice conversion technique on singing voices. A phonetic posterior feature is first generated by decoding singing voices through a robust Automa…
Clustering algorithms have regained momentum with recent popularity of data mining and knowledge discovery approaches. To obtain good clustering in reasonable amount of time, various meta-heuristic approaches and their hybridization, sometimes with K-Means technique, have been employed. A Kalman Filtering based heurist…
RL improves combinatorial optimization by automating heuristic search.
This paper investigates Shampoo's heuristics and decouples preconditioner updates.
Developed Forex trading heuristics with high profit potential.