Speed, Accuracy, and Complexity
This paper re-examines the use of response time to infer problem complexity. It revisits a canonical Wald model of optimal stopping, taking signal-to-noise ratio as a measure of problem complexity. While choice quality is monotone in problem complexity, expected stopping time is inverse U-shaped. Indeed, decisions are fast in both very simple and very complex problems: in simple problems, it is quick to understand which alternative is best, while in complex problems it would be too costly -- an insight which extends to general costly information acquisition models. This non-monotonicity also underlies an ambiguous relationship between response time and ability, whereby higher ability entails slower decisions in very complex problems, but faster decisions in simple problems. Finally, this paper proposes a new method to correctly infer problem complexity based on the finding that distorting incentives in favour of an alternative has a greater effect on choices in more complex problems.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
SCAFFLSA: Taming Heterogeneity in Federated Linear Stochastic Approximation and TD Learning
In this paper, we analyze the sample and communication complexity of the federated linear stochastic approximation (FedLSA) algorithm. We explicitly quantify the effects of local training with agent heterogeneity. We sho…
Efficient Neural Network Compression
Network compression reduces the computational complexity and memory consumption of deep neural networks by reducing the number of parameters. In SVD-based network compression, the right rank needs to be decided for every…
CPUEfficient Neural NetworkNeural Network CompressionApproximate learning of high dimensional Bayesian network structures via pruning of Candidate Parent Sets
Score-based algorithms that learn Bayesian Network (BN) structures provide solutions ranging from different levels of approximate learning to exact learning. Approximate solutions exist because exact learning is generall…
Benchmark Assessment for DeepSpeed Optimization Library
Deep Learning (DL) models are widely used in machine learning due to their performance and ability to deal with large datasets while producing high accuracy and performance metrics. The size of such datasets and the comp…
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
Transformers are slow and memory-hungry on long sequences, since the time and memory complexity of self-attention are quadratic in sequence length. Approximate attention methods have attempted to address this problem by …
16k4kDocument ClassificationGPU+2