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.
The paper investigates how neural network weights evolve to monitor training progress.
Progressive Neural Network Learning is a class of algorithms that incrementally construct the network's topology and optimize its parameters based on the training data. While this approach exempts the users from the manual task of designing and validating multiple network topologies, it often requires an enormous numbe…
We propose Progressive Structure-conditional Generative Adversarial Networks (PSGAN), a new framework that can generate full-body and high-resolution character images based on structural information. Recent progress in generative adversarial networks with progressive training has made it possible to generate high-resol…
This paper explores the trade-off between spatial and adversarial robustness in neural networks.
PaGoDA reduces diffusion model training costs by 64x.
RLVR training dynamics reveal an implicit curriculum that shapes learning progression.
Paper introduces a new curriculum generation method for reinforcement learning.
Curriculum learning speeds up agent learning in Minecraft, a complex visual domain.
Drop-Muon updates only some layers, speeding up training.
Extracting a curriculum from a teacher network improves distillation efficiency.
AI progress measured by reduced compute needed to reach past performance.
Gradient span algorithms show consistent progress in high dimensions.
Deep learning accelerators efficiently train over vast and growing amounts of data, placing a newfound burden on commodity networks and storage devices. A common approach to conserve bandwidth involves resizing or compressing data prior to training. We introduce Progressive Compressed Records (PCRs), a data format that…
We describe a new training methodology for generative adversarial networks. The key idea is to grow both the generator and discriminator progressively: starting from a low resolution, we add new layers that model increasingly fine details as training progresses. This both speeds the training up and greatly stabilizes i…
We present new intuitions and theoretical assessments of the emergence of disentangled representation in variational autoencoders. Taking a rate-distortion theory perspective, we show the circumstances under which representations aligned with the underlying generative factors of variation of data emerge when optimising…
In neural architecture search, the structure of the neural network to best model a given dataset is determined by an automated search process. Efficient Neural Architecture Search (ENAS), proposed by Pham et al. (2018), has recently received considerable attention due to its ability to find excellent architectures with…
We introduce Mix&Match (M&M) - a training framework designed to facilitate rapid and effective learning in RL agents, especially those that would be too slow or too challenging to train otherwise. The key innovation is a procedure that allows us to automatically form a curriculum over agents. Through such a curriculum …
Although deep neural networks (NNs) have achievedstate-of-the-art accuracy in many visual recognition tasks,the growing computational complexity and energy con-sumption of networks remains an issue, especially for ap-plications on platforms with limited resources and requir-ing real-time processing. Filter pruning tech…
Most approaches to machine learning from electronic health data can only predict a single endpoint. Here, we present an alternative that uses unsupervised deep learning to simulate detailed patient trajectories. We use data comprising 18-month trajectories of 44 clinical variables from 1908 patients with Mild Cognitive…
AL2 progressively penalizes network activations to prevent overfitting.
Improved NODEs for long-term time series forecasting.
New approach ties loss curvature to model performance in deep learning.
We use GG distributions to optimize LLMs, reducing size and training time.
Despite the advancement of supervised image recognition algorithms, their dependence on the availability of labeled data and the rapid expansion of image categories raise the significant challenge of zero-shot learning. Zero-shot learning (ZSL) aims to transfer knowledge from labeled classes into unlabeled classes to r…
Deep nearest neighbors outperform self-supervised methods in anomaly detection.
We introduce a conceptually simple and scalable framework for continual learning domains where tasks are learned sequentially. Our method is constant in the number of parameters and is designed to preserve performance on previously encountered tasks while accelerating learning progress on subsequent problems. This is a…
We explore a new way to evaluate generative models using insights from evaluation of competitive games between human players. We show experimentally that tournaments between generators and discriminators provide an effective way to evaluate generative models. We introduce two methods for summarizing tournament outcomes…
Proposes a curriculum-based scheme to smooth CNN feature embeddings.
High volume of data, perceived as either challenge or opportunity. Deep learning architecture demands high volume of data to effectively back propagate and train the weights without bias. At the same time, large volume of data demands higher capacity of the machine where it could be executed seamlessly. Budding data sc…
In this work, we provide an efficient and realistic data-driven approach to simulate astronomical images using deep generative models from machine learning. Our solution is based on a variant of the generative adversarial network (GAN) with progressive training methodology and Wasserstein cost function. The proposed so…
Adversarial images are designed to mislead deep neural networks (DNNs), attracting great attention in recent years. Although several defense strategies achieved encouraging robustness against adversarial samples, most of them fail to improve the robustness on common corruptions such as noise, blur, and weather/digital …
A new principle for extrapolating regression outside training data.
In this paper we introduce Curriculum GANs, a curriculum learning strategy for training Generative Adversarial Networks that increases the strength of the discriminator over the course of training, thereby making the learning task progressively more difficult for the generator. We demonstrate that this strategy is key …
Proposes a progressive label correction method for feature-dependent label noise.
Fastens diffusion model sampling by distillation.
We propose a novel neural architecture search algorithm via reinforcement learning by decoupling structure and operation search processes. Our approach samples candidate models from the multinomial distribution on the policy vectors defined on the two search spaces independently. The proposed technique improves the eff…
Multiple Sclerosis (MS) is a neurodegenerative disorder characterized by a complex set of clinical assessments. We use an unsupervised machine learning model called a Conditional Restricted Boltzmann Machine (CRBM) to learn the relationships between covariates commonly used to characterize subjects and their disease pr…
Bayesian meta-learning predicts Alzheimer's disease progression.
In this paper, we investigate a new form of automated curriculum learning based on adaptive selection of accuracy requirements, called accuracy-based curriculum learning. Using a reinforcement learning agent based on the Deep Deterministic Policy Gradient algorithm and addressing the Reacher environment, we first show …
PTSD improves neural samplers by combining diffusion models and PT, enhancing efficiency.
In this article, we investigate when the set of primitive geodesic lengths on a Riemannian manifold have arbitrarily long arithmetic progressions. We prove that in the space of negatively curved metrics, a metric having such arithmetic progressions is quite rare. We introduce almost arithmetic progressions, a coarsific…
Study examines APOE's impact on AD progression using a novel DEBM approach.
PS-KD distills a model's own knowledge to soften hard targets during training.
Deep learning predicts AMD progression from longitudinal fundus images.
Generative Adversarial Networks are a new family of generative models, frequently used for generating photorealistic images. The theory promises for the GAN to eventually reach an equilibrium where generator produces pictures indistinguishable for the training set. In practice, however, a range of problems frequently p…
Develops a new method to create object models from medical images.
Weight decay stabilizes training dynamics by slowing progressive sharpening.
The study analyzes sharpness dynamics in neural networks, revealing mechanisms and conditions.