Learning from discriminative feature feedback
Authors: Sanjoy Dasgupta, Akansha Dey, Nicholas Roberts, Sivan Sabato
NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We also demonstrate the learning procedure experimentally. The ZOO data set from the UCI ML repository contains information on 101 animals... The learning algorithm of Figure 2 can potentially return different classifiers depending on the particular ordering of the data points. Figure 3 shows the result of one run. |
| Researcher Affiliation | Academia | Sanjoy Dasgupta, Akansha Dey, Nicholas Roberts Department of Computer Science and Engineering University of California, San Diego dasgupta@eng.ucsd.edu,n3robert@ucsd.edu,a1dey@ucsd.edu Sivan Sabato Department of Computer Science Ben-Gurion University of the Negev sabatos@cs.bgu.ac.il |
| Pseudocode | Yes | Figure 2: An algorithm that learns from discriminative feature feedback. Initialization: Get the label yo of the first example xo (these serve as a default prediction) Initialize L to an empty list At time t, given a new point xt: If there exists bx 2 L such that xt satisfies C[bx]: Predict label[bx] and provide example bx If incorrect: Get correct label yt and feature φ C[bx] := C[bx] φ Else: Predict default label yo and provide example xo If incorrect: Get correct label yt and feature φ Add xt to L Set label[xt] := yt and C[xt] := φ |
| Open Source Code | No | The paper does not provide any explicit statement about open-sourcing the code for the described methodology, nor does it provide a link to a code repository. |
| Open Datasets | Yes | The ZOO data set from the UCI ML repository contains information on 101 animals |
| Dataset Splits | No | The paper mentions using the ZOO dataset and conducting an experiment, but it does not specify any training, validation, or test splits (e.g., percentages or counts) or cross-validation setup for reproducibility. It describes 'one run' but not how the data was partitioned for that run. |
| Hardware Specification | No | The paper does not provide specific details about the hardware (e.g., GPU/CPU models, memory) used to run the experiments. |
| Software Dependencies | No | The paper does not specify any software dependencies with version numbers (e.g., programming languages, libraries, or specific solvers). |
| Experiment Setup | No | The paper describes the online learning process and that 'a separating feature is chosen at random from those that distinguish the two instances' in the experiment. However, it does not provide explicit hyperparameters (like learning rate, batch size, epochs) or other system-level training configurations typically found in experimental setups for deep learning or similar models. |