DARTS fails to generalize well; adding regularization improves robustness.
problem DARTS fails to find architectures that generalize well across different tasks.
method Identified failure modes, added regularization, proposed variations.
result Regularization robustifies DARTS to find better generalizing architectures.
RARTS improves neural architecture search efficiency and accuracy.
problem Efficiency and accuracy issues in first-order DARTS.
method Formulates a relaxed architecture search (RARTS) method that uses whole dataset splitting.
result RARTS outperforms DARTS and its variants in accuracy and efficiency.
DARTS- improves robustness by factoring out skip connections' advantage.
problem Performance collapse in DARTS architecture search.
method Factor out skip connections' advantage with an auxiliary skip connection.
result Significantly improved robustness across various datasets.
Paper stabilizes DARTS algorithm for better neural architecture search.
problem Weak stability of DARTS algorithm leading to unreliable results.
method Amended gradient estimation method to bridge optimization gap.
result Significant improvement in search stability and larger search spaces explored.
Theory explains why DARTS favors deep architectures over shallow ones.
problem DARTS selects architectures with dominated skip connections, leading to performance degradation.
method Theoretical analysis of operations' effects on network optimization; introduces sparse binary gates and path-depth-wise regularization.
result Theoretical proof that architectures with more skip connections converge faster.
New hierarchical search algorithm improves neural architecture design across different operator sets.
problem DARTS's performance drops when search space changes due to operator correlation and optimization complexity.
method Operator clustering and optimization complexity matching in a hierarchical search algorithm.
result The algorithm consistently finds high-performance architectures across various search spaces, outperforming other methods.
Paper tackles unfair advantages in DARTS, presenting Fair DARTS to improve neural architecture search.
problem Performance collapse in DARTS due to unfair advantages in skip connections.
method Relax exclusive competition to collaborative, let architectural weights be independent, and use zero-one loss for discretization.
result New state-of-the-art results on CIFAR-10 and ImageNet, demonstrating the effectiveness of Fair DARTS.
SmoothDARTS stabilizes DARTS-based architecture search by smoothing loss landscapes.
problem DARTS-based NAS methods suffer from instability, leading to deteriorating architectures.
method SmoothDARTS (SDARTS) uses perturbation-based regularization to smooth the loss landscape.
result SmoothDARTS improves the generalizability and performance of DARTS-based methods.
DART optimizes subset selection in non-linear bandit problems.
problem Optimizing subset selection in non-linear bandit problems with correlated rewards.
method DART algorithm for combinatorial bandits without individual arm feedback or linearity assumption.
result DART achieves a regret bound of i l d e O ( K K N T ) ilde{\mathcal{O}}(K\sqrt{KNT}) i l d e O ( K K N T ) . 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.
problem Forecasting and optimizing day-ahead versus real-time price spreads in U.S. electricity markets.
method Unified statistical model for positive and negative spikes, structural price impact model based on bid stacks.
result Optimal trading strategy improves risk-return profile and highlights market heterogeneity.
NASP uses proximal gradient descent to speed up neural architecture search.
problem Efficiently search for high-performance neural architectures.
method Differentiable Neural Architecture Search using Proximal gradient descent.
result NASP achieves 10 times speedup over DARTS while maintaining high performance.
DART tackles adversarial robustness in domain adaptation without labeled target data.
problem Combining distribution shifts and adversarial examples in unsupervised domain adaptation.
method DART framework that combines standard UDA methods with a generalization bound for adversarial target loss.
result DART significantly enhances model robustness to adversarial attacks compared to state-of-the-art methods.
DARTS optimizes covariate selection in trials with limited data.
problem Limited budget for high-dimensional pretreatment data.
method Dynamic Adaptive Rerandomization via Thompson Sampling (DARTS).
result DARTS efficiently concentrates budget on informative features.
Prune and Replace NAS expands search space for faster network discovery.
problem Limited search space in recent NAS algorithms.
method Progressively prunes and replaces candidates to explore a larger search space.
result Achieves state-of-the-art error rates on CIFAR datasets.
Paper proposes an iterative NAS technique inspired by Boolean function learning.
problem Challenges in Neural Architecture Search (NAS).
method Inspired by algorithms for learning low-degree sparse Boolean functions.
result Validated on DARTs and NAS-Bench-201, providing theoretical analysis.
In this paper we derive a generating series for the number of cellular complexes known as pavings or three-dimensional maps, on n n n darts, thus solving an analogue of Tutte's problem in dimension three. The generating series we derive also counts free subgroups of index n n n in $Δ^+ = \mathbb{Z}_2*\mathbb{Z}_2*\mathbb{Z…
A method to reduce memory usage in NAS by pruning the search space.
problem High GPU memory consumption in One-Shot NAS techniques.
method Utilising Zero-Shot NAS to prune the search space before applying One-Shot NAS.
result Reduces memory consumption by 81% while maintaining accuracy.
A new neural network model for predicting event times without distributional assumptions.
problem Predicting event times from censored data with complex assumptions.
method Deep AFT Rank-regression model (DART) using Gehan's rank statistic.
result DART significantly improves performance on various benchmark datasets.
NoisyDARTS injects random noise to improve neural architecture search.
problem Performance collapse in Differentiable Architecture Search (DARTS).
method Inject unbiased random noise to skip connections to impede gradient flow.
result NoisyDARTS achieves state-of-the-art results across various tasks.
MetaNAS improves few-shot learning by optimizing neural architectures with meta-learning.
problem Few-shot learning challenges due to limited data and compute time.
method MetaNAS integrates NAS with gradient-based meta-learning to adapt neural architectures to new tasks efficiently.
result MetaNAS achieves state-of-the-art results on few-shot classification benchmarks.
New distance metric for neural architecture search reduces search space complexity.
problem Reducing the complexity of neural architecture search.
method Fisher task distance for measuring task similarity and online neural architecture search.
result Reduced search space complexity for task-specific architectures.
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…
Random investment strategies outperform sensible ones, even with forecasts.
problem The usefulness of investment strategies based on forecasts is questioned.
method Investigated the performance of sensible and nonsensical investment strategies, including forecasts.
result There is no substantial difference between the performances of ``best'' and ``trivial'' 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…
NAS favors wide and shallow cell structures, leading to fast convergence but not necessarily better generalization.
problem Understanding and improving the architectures generated by NAS algorithms.
method Empirical and theoretical study of existing NAS algorithms (DARTS, ENAS) and their architectures.
result Existing NAS algorithms favor wide and shallow cell structures, leading to fast convergence but not necessarily better generalization.
MiLeNAS improves neural architecture search by reducing approximation errors and achieving better accuracy.
problem Improving efficiency and accuracy in neural architecture search (NAS).
method Mixed-level reformulation (MiLeNAS) to optimize efficiently and reliably.
result MiLeNAS achieves lower validation error and higher accuracy than bilevel optimization methods.
New algorithms improve neural architecture search with faster convergence.
problem Improving efficiency and accuracy of neural architecture search.
method Geometry-aware gradient algorithms to optimize continuous relaxation of discrete search spaces.
result Exceeds state-of-the-art results on CIFAR and ImageNet benchmarks.
Unified comparison of gradient boosting algorithms for insurance claims.
problem Improving predictive accuracy and computational efficiency in insurance claim prediction.
method Unified notation and comprehensive numerical study comparing 12 gradient boosting algorithms on 5 datasets.
result No trade-off between model adequacy and predictive accuracy.
WASH trains ensembles with shuffled weights to improve accuracy and reduce communication.
problem Training ensembles for weight averaging leads to models converging to different loss basins.
method WASH randomly shuffles a small percentage of weights during training to keep models within the same basin.
result WASH achieves state-of-the-art image classification accuracy with lower communication costs.
NPENAS improves neural architecture search efficiency and accuracy.
problem Efficient and accurate neural architecture search (NAS) for minimizing search costs.
method Proposes NPENAS, a neural predictor guided evolutionary algorithm that enhances exploration ability of evolutionary algorithms.
result NPENAS-BO and NPENAS-NP outperform existing NAS algorithms on NASBench-201, NASBench-101, and DARTS.
UNAS combines DNAS and RL for efficient architecture search.
problem Discovering high accuracy or low latency neural architectures.
method Unified framework combining differentiable and reinforcement learning approaches.
result UNAS achieves state-of-the-art accuracy on CIFAR-10, CIFAR-100, and ImageNet datasets.
BRP-NAS uses GCNs to predict neural network performance for more efficient NAS.
problem Inaccurate performance metrics in NAS lead to suboptimal model designs.
method Proposes BRP-NAS, a hardware-aware NAS using GCNs for accurate performance prediction.
result BRP-NAS outperforms previous methods on NAS-Bench-101 and 201, improving model sample efficiency.
New algorithms improve privacy and utility of large language models.
problem Privacy-preserving fine-tuning of large language models.
method Meta-framework for differentially private fine-tuning, inspired by recent success in fine-tuning.
result Private fine-tuned models achieve utility close to non-private models, with improved privacy and efficiency.
DiSK improves DP optimizers by simplifying Kalman filtering for better performance.
problem Performance drop of DP optimizers in large-scale training due to noise injection.
method DiSK uses Kalman filtering to denoise privatized gradients and refine gradient estimations.
result DiSK achieves significant performance improvements over standard DP optimizers in large-scale training.
This work explores how neural architecture search can improve adversarial robustness without adversarial training.
problem Improving adversarial robustness of neural networks without adversarial training.
method Experimented with hand-crafted and NAS-based architectures to compare robustness to PGD attacks.
result NAS-based architectures are more robust for small-scale attacks, but hand-crafted architectures are more robust for larger datasets and tasks.
NAS evaluation is hard due to lack of standard protocols.
problem Difficulty in comparing NAS methods due to varying search spaces and evaluation protocols.
method Benchmarked 8 NAS methods on 5 datasets, proposing a relative improvement metric over random architectures.
result Many NAS techniques struggle to significantly outperform a randomly generated architecture.