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.
DBQ quantizes lightweight networks efficiently for resource-constrained devices.
Optimizes neural architecture search to generate novel lightweight models.
GIBLy adds geometric priors to 3D segmentation models, improving performance with minimal overhead.
BERTino is a lightweight Italian DistilBERT model for NLP tasks.
Mapper-GIN simplifies 3D point cloud classification with lightweight structure.
A novel framework combines LLMs and RL for financial portfolio optimization.
Machine Reading Comprehension (MRC) is an important topic in the domain of automated question answering and in natural language processing more generally. Since the release of the SQuAD 1.1 and SQuAD 2 datasets, progress in the field has been particularly significant, with current state-of-the-art models now exhibiting…
Paper proposes GP-NAS-ensemble for fast neural architecture performance prediction.
In this paper, we integrate VAEs and flow-based generative models successfully and get f-VAEs. Compared with VAEs, f-VAEs generate more vivid images, solved the blurred-image problem of VAEs. Compared with flow-based models such as Glow, f-VAE is more lightweight and converges faster, achieving the same performance und…
VALAN is a lightweight and scalable software framework for deep reinforcement learning based on the SEED RL architecture. The framework facilitates the development and evaluation of embodied agents for solving grounded language understanding tasks, such as Vision-and-Language Navigation and Vision-and-Dialog Navigation…
DeepDyve uses simpler neural networks to verify DNNs for faults.
A new data-level recombination strategy improves RGB-D salient object detection.
Deep neural networks and decision trees operate on largely separate paradigms; typically, the former performs representation learning with pre-specified architectures, while the latter is characterised by learning hierarchies over pre-specified features with data-driven architectures. We unite the two via adaptive neur…
We develop a progressive training approach for neural networks which adaptively grows the network structure by splitting existing neurons to multiple off-springs. By leveraging a functional steepest descent idea, we derive a simple criterion for deciding the best subset of neurons to split and a splitting gradient for …
A new framework for lightweight BNNs learns heteroscedastic uncertainties efficiently.
Neuro-inspired recurrent neural network algorithms, such as echo state networks, are computationally lightweight and thereby map well onto untethered devices. The baseline echo state network algorithms are shown to be efficient in solving small-scale spatio-temporal problems. However, they underperform for complex task…
Even though probabilistic treatments of neural networks have a long history, they have not found widespread use in practice. Sampling approaches are often too slow already for simple networks. The size of the inputs and the depth of typical CNN architectures in computer vision only compound this problem. Uncertainty in…
Convolutional neural networks are widely adopted in Acoustic Scene Classification (ASC) tasks, but they generally carry a heavy computational burden. In this work, we propose a lightweight yet high-performing baseline network inspired by MobileNetV2, which replaces square convolutional kernels with unidirectional ones …
RSAC improves lightweight continuous learning efficiency.
DLC enhances distillation-based continual learning with lightweight plugins.
iSTFTNet2 improves iSTFTNet's speed and lightness with 1D-2D CNN.
Self-paced learning and hard example mining re-weight training instances to improve learning accuracy. This paper presents two improved alternatives based on lightweight estimates of sample uncertainty in stochastic gradient descent (SGD): the variance in predicted probability of the correct class across iterations of …
Augment small datasets with synthetic backgrounds to train lightweight CNNs for human pose estimation.
A new RNN architecture reduces model size and improves performance.
MetaPerturb learns to improve generalization across different tasks and architectures.
CMoS improves time series forecasting with minimal parameters.
Federated learning framework improves model generalization and privacy.
When using reinforcement learning (RL) algorithms it is common, given a large state space, to introduce some form of approximation architecture for the value function (VF). The exact form of this architecture can have a significant effect on an agent's performance, however, and determining a suitable approximation arch…
The deployment of deep neural networks in real-world applications is mostly restricted by their high inference costs. Extensive efforts have been made to improve the accuracy with expert-designed or algorithm-searched architectures. However, the incremental improvement is typically achieved with increasingly more expen…
CogScale benchmarks AI architectures for sequential processing.
Learn to automatically plug domain-specific modules into a common network.
Winograd convolutions are used to improve quantized neural networks.
DecompKAN improves time series forecasting accuracy and transparency.
Optimizes neural networks by removing unnecessary layers, improving performance and speed.
We present a machine learning-based approach to lossy image compression which outperforms all existing codecs, while running in real-time. Our algorithm typically produces files 2.5 times smaller than JPEG and JPEG 2000, 2 times smaller than WebP, and 1.7 times smaller than BPG on datasets of generic images across all …
TinyXRA assesses financial risks from 10-K reports using a lightweight transformer model.
P-OCS detects OOD samples in a low-dimensional subspace, outperforming existing methods.
Coresets are compact representations of data sets such that models trained on a coreset are provably competitive with models trained on the full data set. As such, they have been successfully used to scale up clustering models to massive data sets. While existing approaches generally only allow for multiplicative appro…
When confronted with a substance of unknown identity, researchers often perform mass spectrometry on the sample and compare the observed spectrum to a library of previously-collected spectra to identify the molecule. While popular, this approach will fail to identify molecules that are not in the existing library. In r…
We introduce an adaptive output-sensitive Metropolis-Hastings algorithm for probabilistic models expressed as programs, Adaptive Lightweight Metropolis-Hastings (AdLMH). The algorithm extends Lightweight Metropolis-Hastings (LMH) by adjusting the probabilities of proposing random variables for modification to improve c…
New model mimics neural next item recommendation using Hankel matrices.
ALIEN improves uncertainty estimation of language models by refining entropy-based methods.
A lightweight framework improves convergence and stability of PINNs for complex PDEs.
Our goal is to design architectures that retain the groundbreaking performance of CNNs for landmark localization and at the same time are lightweight, compact and suitable for applications with limited computational resources. To this end, we make the following contributions: (a) we are the first to study the effect of…
Executing deep neural networks for inference on the server-class or cloud backend based on data generated at the edge of Internet of Things is desirable due primarily to the limited compute power of edge devices and the need to protect the confidentiality of the inference neural networks. However, such a remote inferen…
Deploying trained convolutional neural networks (CNNs) to mobile devices is a challenging task because of the simultaneous requirements of the deployed model to be fast, lightweight and accurate. Designing and training a CNN architecture that does well on all three metrics is highly non-trivial and can be very time-con…
Paper presents a hybrid framework combining sentiment analysis and market indicators for financial portfolio optimization.
Detect knots from photos using machine learning and traditional algorithms.