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.
RARTS improves neural architecture search efficiency and accuracy.
Differentiable Architecture Search (DARTS) has attracted a lot of attention due to its simplicity and small search costs achieved by a continuous relaxation and an approximation of the resulting bi-level optimization problem. However, DARTS does not work robustly for new problems: we identify a wide range of search spa…
DARTS- improves robustness by factoring out skip connections' advantage.
Theory explains why DARTS favors deep architectures over shallow ones.
SmoothDARTS stabilizes DARTS-based architecture search by smoothing loss landscapes.
Neural architecture search (NAS) recently attracts much research attention because of its ability to identify better architectures than handcrafted ones. However, many NAS methods, which optimize the search process in a discrete search space, need many GPU days for convergence. Recently, DARTS, which constructs a diffe…
Recently, the efficiency of automatic neural architecture design has been significantly improved by gradient-based search methods such as DARTS. However, recent literature has brought doubt to the generalization ability of DARTS, arguing that DARTS performs poorly when the search space is changed, i.e, when different s…
DART optimizes subset selection in non-linear bandit problems.
Multiple Additive Regression Trees (MART), an ensemble model of boosted regression trees, is known to deliver high prediction accuracy for diverse tasks, and it is widely used in practice. However, it suffers an issue which we call over-specialization, wherein trees added at later iterations tend to impact the predicti…
Model predicts and optimizes trading of electricity price spreads across multiple zones.
DART tackles adversarial robustness in domain adaptation without labeled target data.
DARTS optimizes covariate selection in trials with limited data.
DARTS is a popular algorithm for neural architecture search (NAS). Despite its great advantage in search efficiency, DARTS often suffers weak stability, which reflects in the large variation among individual trials as well as the sensitivity to the hyper-parameters of the search process. This paper owes such instabilit…
Differentiable Architecture Search (DARTS) is now a widely disseminated weight-sharing neural architecture search method. However, it suffers from well-known performance collapse due to an inevitable aggregation of skip connections. In this paper, we first disclose that its root cause lies in an unfair advantage in exc…
While recent NAS algorithms are thousands of times faster than the pioneering works, it is often overlooked that they use fewer candidate operations, resulting in a significantly smaller search space. We present PR-DARTS, a NAS algorithm that discovers strong network configurations in a much larger search space and a s…
In this paper we derive a generating series for the number of cellular complexes known as pavings or three-dimensional maps, on darts, thus solving an analogue of Tutte's problem in dimension three. The generating series we derive also counts free subgroups of index in $Δ^+ = \mathbb{Z}_2*\mathbb{Z}_2*\mathbb{Z…
A method to reduce memory usage in NAS by pruning the search space.
A new neural network model for predicting event times without distributional assumptions.
NoisyDARTS injects random noise to improve neural architecture search.
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…
New distance metric for neural architecture search reduces search space complexity.
This paper addresses the scalability challenge of architecture search by formulating the task in a differentiable manner. Unlike conventional approaches of applying evolution or reinforcement learning over a discrete and non-differentiable search space, our method is based on the continuous relaxation of the architectu…
We introduce a method for constructing skills capable of solving tasks drawn from a distribution of parameterized reinforcement learning problems. The method draws example tasks from a distribution of interest and uses the corresponding learned policies to estimate the topology of the lower-dimensional piecewise-smooth…
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…
Neural architecture search (NAS) searches architectures automatically for given tasks, e.g., image classification and language modeling. Improving the search efficiency and effectiveness have attracted increasing attention in recent years. However, few efforts have been devoted to understanding the generated architectu…
Random investment strategies outperform sensible ones, even with forecasts.
The efficient market hypothesis has been considered one of the most controversial arguments in finance, with the academia divided between who claims the impossibility of beating the market and who believes that it is possible to gain over the average profits. If the hypothesis holds, it means, as suggested by Burton Ma…
MiLeNAS improves neural architecture search by reducing approximation errors and achieving better accuracy.
New algorithms improve neural architecture search with faster convergence.
Unified comparison of gradient boosting algorithms for insurance claims.
WASH trains ensembles with shuffled weights to improve accuracy and reduce communication.
Neural architecture search (NAS) aims to discover network architectures with desired properties such as high accuracy or low latency. Recently, differentiable NAS (DNAS) has demonstrated promising results while maintaining a search cost orders of magnitude lower than reinforcement learning (RL) based NAS. However, DNAS…
NPENAS improves neural architecture search efficiency and accuracy.
BRP-NAS uses GCNs to predict neural network performance for more efficient NAS.
New algorithms improve privacy and utility of large language models.
DiSK improves DP optimizers by simplifying Kalman filtering for better performance.
Neural Architecture Search (NAS) is an exciting new field which promises to be as much as a game-changer as Convolutional Neural Networks were in 2012. Despite many great works leading to substantial improvements on a variety of tasks, comparison between different methods is still very much an open issue. While most al…
This work explores how neural architecture search can improve adversarial robustness without adversarial training.