Add overview pages to documentation

NASLib_docs/docs/optimizers/overview.md

@@ -0,0 +1,37 @@
+# Optimizers Documentation Overview
+
+This documentation provides information on a range of optimizers available in NASLib. Explore these optimizers for both discrete and one-shot architecture search methods, each tailored to specific tasks within the NAS field.
+
+## Discrete Optimizers
+
+### 1. [Bananas](discrete/bananas.md)
+Bananas is a powerful discrete optimizer that can efficiently search for neural architectures in a discrete search space. It employs a combination of Bayesian optimization and neural networks to find optimal architectures.
+
+### 2. [Base Predictor](discrete/bp.md)
+The Base Predictor optimizer is a foundational component for discrete NAS. It provides a starting point for architecture search by predicting the performance of candidate architectures based on historical data.
+
+### 3. [Local Search](discrete/ls.md)
+Local Search is an optimizer that focuses on refining neural architectures through local exploration. It is a valuable tool for fine-tuning architectures to achieve better performance.
+
+### 4. [NPenas](discrete/npenas.md)
+NPenas is an optimizer that leverages penalization-based techniques to search for neural architectures. It helps prevent overfitting while finding architectures that perform well on your specific task.
+
+### 5. [Regularized Evolution](discrete/re.md)
+Regularized Evolution is a discrete optimizer that uses evolutionary algorithms with regularization to discover high-performing neural architectures. It balances exploration and exploitation to find optimal solutions.
+
+### 6. [Random Search](discrete/rs.md)
+Random Search is a simple yet effective optimizer that explores neural architecture search spaces by randomly sampling and evaluating architectures. It serves as a baseline for NAS experiments.
+
+## One-Shot Optimizers
+
+### 7. [DARTS](oneshot/darts.md)
+DARTS (Differentiable Architecture Search) is a one-shot optimizer that uses gradient-based methods to search for optimal neural architectures. It allows the continuous relaxation of the architecture search space for efficiency.
+
+### 8. [DrNAS](oneshot/drnas.md)
+DrNAS is an optimizer that incorporates regularization techniques into one-shot NAS. It focuses on discovering robust neural architectures by adding regularization constraints during the search process.
+
+### 9. [GDAS](oneshot/gdas.md)
+GDAS (Gradient-Driven Architecture Search) is a one-shot optimizer that emphasizes the use of gradients to guide the search for neural architectures. It efficiently explores the search space while maintaining differentiability.
+
+### 10. [RSWS](oneshot/rsws.md)
+ RSWS (Random Search with Weight Sharing) is a one-shot optimizer that combines random search with weight sharing to discover neural architectures efficiently. It leverages shared weights to speed up the search process.

NASLib_docs/docs/search_spaces/overview.md

@@ -0,0 +1,24 @@
+# Search Spaces Overview
+
+This documentation offers insights into a variety of search spaces within NASLib. Delve into these search spaces designed to address specific tasks and domains, and tailor your architecture search experiments accordingly.
+
+## 1. [NAS-Bench-101](nasbench_101.md)
+NAS-Bench-101 provides a comprehensive search space for evaluating neural architectures in the context of computer vision tasks. It is a valuable resource for benchmarking and comparison.
+
+## 2. [NAS-Bench-201](nasbench_201.md)
+NAS-Bench-201 is designed to support architecture search for various tasks, including computer vision and beyond. It offers diverse search spaces to cater to different application domains.
+
+## 3. [NAS-Bench-301](nasbench_301.md)
+NAS-Bench-301 extends the capabilities of our library by providing a versatile search space for exploring neural architectures in the context of computer vision and related fields.
+
+## 4. [NAS-Bench-ASR](nasbench_asr.md)
+NAS-Bench-ASR is tailored for the domain of Automatic Speech Recognition (ASR). It offers specific search spaces and configurations optimized for ASR tasks.
+
+## 5. [NAS-Bench-NLP](nasbench_nlp.md)
+NAS-Bench-NLP focuses on Natural Language Processing (NLP) tasks, providing search spaces designed to create and evaluate neural architectures for NLP applications.
+
+## 6. [Simple Cell](simple_cell.md)
+Simple Cell is a straightforward and customizable search space that can be used for a variety of NAS experiments. It allows researchers to define and explore their own architectures.
+
+## 7. [Transbench 101](transbench101.md)
+Transbench 101 is a specialized search space designed for transformer-based models, suitable for a wide range of tasks, including language modeling and machine translation.

NASLib_docs/mkdocs.yml

@@ -28,8 +28,7 @@ nav:
         - NAS-Bench-NLP: search_spaces/nasbench_nlp.md
         - Simple Cell: search_spaces/simple_cell.md
         - Transbench101: search_spaces/transbench101.md
-    - Utils:
-        - Overview: utils/overview.md
+    # TODO Utils
     - Contributing: contributing.md
 plugins:
   - mkdocstrings: