Minimizing Adaptive Regret with One Gradient per Iteration
Authors: Guanghui Wang, Dakuan Zhao, Lijun Zhang
IJCAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In this section, we present empirical results on different data sets to evaluate the proposed algorithms. ... Empirical results demonstrate the efficiency and effectiveness of our methods. |
| Researcher Affiliation | Academia | Guanghui Wang, Dakuan Zhao, Lijun Zhang National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023, China wanggh@lamda.nju.edu.cn, zdk@smail.nju.edu.cn, zhanglj@lamda.nju.edu.cn |
| Pseudocode | Yes | Algorithm 1 The meta algorithm for exp-concave and strongly convex functions... Algorithm 2 The algorithm for expert Ei (exp-concave version)... Algorithm 3 The algorithm for expert Ei (strongly convex version)... Algorithm 4 The meta algorithm for general convex functions... Algorithm 5 The algorithm for expert Ei (general convex version) |
| Open Source Code | No | The paper does not provide any explicit statements or links indicating that the source code for the described methodology is publicly available. |
| Open Datasets | Yes | Following the same spirit as in Section 4.1., We build a dynamic scenario based on real-world binary classification data set IJCNN01 [Prokhorov, 2001; Chang and Lin, 2011]. |
| Dataset Splits | No | The paper describes how data is sampled over iterations for dynamic scenarios, but it does not specify traditional train/validation/test splits (e.g., percentages or counts) for a fixed dataset. For IJCNN01, it describes a dynamic data usage pattern over 9000 iterations, where training data batches arrive and labels are flipped in certain intervals, rather than defining static data splits for training, validation, and testing. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware used for running the experiments (e.g., CPU, GPU models, memory). |
| Software Dependencies | No | The paper does not list specific software dependencies with version numbers used in the experiments. |
| Experiment Setup | Yes | Following Jun et al. [2017], we scale both loss and surrogate loss by assigning a = 500 and capping them above at 1. The value of b is empirically set as 10 4. ... We set n = 256 for both algorithms. ... To make Assumption 2 is satisfied, we also add a domain constraint such that the optimal parameters are inside a d-dimensional ball with radius 10. |