Filters








2 Hits in 1.1 sec

Programming by Rewards [article]

Nagarajan Natarajan, Ajaykrishna Karthikeyan, Prateek Jain, Ivan Radicek, Sriram Rajamani, Sumit Gulwani, Johannes Gehrke
2020 arXiv   pre-print
Karthikeyan, Prateek Jain, Ivan Radiček, Sriram Rajamani, Sumit Gulwani, and Johannes Gehrke double Aircraft(double v1, double v2) {  ...  else return 0.81; else if (y >= -0.01*x -0.41) if (y >= 0.01*x + 0.43) return 0.3; else return 0; else if (0.94*x >= 0.34*y + 2.58) return 0.47; else return 1; } Nagarajan Natarajan, Ajaykrishna  ... 
arXiv:2007.06835v1 fatcat:5m4jvpf37jhf5mys2zixsc6ccu

Learning Accurate Decision Trees with Bandit Feedback via Quantized Gradient Descent [article]

Ajaykrishna Karthikeyan, Naman Jain, Nagarajan Natarajan, Prateek Jain
2022 arXiv   pre-print
Decision trees provide a rich family of highly non-linear but efficient models, due to which they continue to be the go-to family of predictive models by practitioners across domains. But learning trees is challenging due to their discrete decision boundaries. The state-of-the-art (SOTA) techniques resort to (a) learning soft trees thereby losing logarithmic inference time; or (b) using methods tailored to specific supervised learning settings, requiring access to labeled examples and loss
more » ... ion. In this work, by leveraging techniques like overparameterization and straight-through estimators, we propose a unified method that enables accurate end-to-end gradient based tree training and can be deployed in a variety of settings like offline supervised learning and online learning with bandit feedback. Using extensive validation on standard benchmarks, we demonstrate that our method provides best of both worlds, i.e., it is competitive to, and in some cases more accurate than methods designed specifically for the supervised settings; and in bandit settings, where most existing tree learning techniques are not applicable, our models are still accurate and significantly outperform the applicable SOTA methods.
arXiv:2102.07567v3 fatcat:t6j5irfkijgbfne5adhudjbova