tensorflow

adanet

Jupyter Notebook2018–2021

tensorflow / adanet · Archived

adanet

Fast and flexible AutoML with learning guarantees.

Explore on GitHub Read Hacker News discussions

6Distinct people

7Mentions

0Explicit recommenders

3.5KGitHub stars

REPOSITORY AT A GLANCE

What to know before exploring

What it is

Fast and flexible AutoML with learning guarantees.

GitHub

Where it is used

No documented product use has been verified yet.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 12:54:37 PM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by year7 dated mentions

Observed mentions: 2018-10-30 17:16:19 UTC to 2021-11-13 14:10:46 UTC.

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges

UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
Period	Start (UTC)	End (exclusive, UTC)	Mentions	Submissions	Comments
2018	2018-01-01 00:00:00 UTC	2019-01-01 00:00:00 UTC	5	1	4
2019	2019-01-01 00:00:00 UTC	2020-01-01 00:00:00 UTC	0	0	0
2020	2020-01-01 00:00:00 UTC	2021-01-01 00:00:00 UTC	1	0	1
2021	2021-01-01 00:00:00 UTC	2022-01-01 00:00:00 UTC	1	0	1

What Hacker News says

7 sources

mark_l_watson·Nov 13, 2021

Looks like a nice project. I just bookmarked it to try sometime. At a previous job, my boss wanted me to spend time on AutoML. I based my work on Google’s AdaNet [1] that did architecture search inside a single TensorFlow session. Unfortunately that project seems to have been abandoned. [1] https://github.com/tensorflow/adanet

In Show HN: AutoAI – A framework to find the best performing AI/ML model

eugenhotaj·Mar 30, 2020

I disagree, PAC bounds are usually way too loose to be useful in practice when it comes to NNs. I think part of the reason is that the way we measure model complexity for NNs does not correspond very well with their ability to generalize, as we've seen with recent papers like deep double descent [1]. Anecdotally, I was of the main authors of the AdaNet framework [2] where we used (approximate) Rademacher complexity (closely related to PAC) to bound the complexity of our learned ensemble models. We never got good results using the complexity measure and would basically turn it off for any practical problem we solved. [1]: https://openai.com/blog/deep-double-descent [2]: https://github.com/tensorflow/adanet

In When to assume neural networks can solve a problem

Michaelanjello·Dec 3, 2018

https://github.com/tensorflow/adanet looks effectively modular to me, although I wouldn't consider it the epitome of the same. One needs to be able to merge, move, and remove modules too.

In Ask HN: Are modular neural networks an interesting avenue for further research?

echan00·Nov 1, 2018Submission

Fast and flexible AutoML with learning guarantees

2 points · Open discussion

cweill·Oct 30, 2018

We have an example of AdaNet on GitHub that uses several complex CNN layers (conv2d, pooling, linearly-separable layers) as part of the NASNet-A architecture (presented in https://arxiv.org/abs/1707.07012): https://github.com/tensorflow/adanet/blob/master/adanet/exam... AdaNet supports high level APIs (e.g tf.layers, tf.losses), so it can support RNN cells as well.

In Introducing AdaNet: Fast and Flexible AutoML with Learning Guarantees

cweill·Oct 30, 2018

We started with Estimator because it’s the easiest to train and deploy with production infrastructure. Having a Keras model API is a good idea: it would make it easier to try AdaNet. Feel free to file a feature request on the GitHub repo: https://github.com/tensorflow/adanet.

In Introducing AdaNet: Fast and Flexible AutoML with Learning Guarantees

minimaxir·Oct 30, 2018

Example notebook from the official repo which gives a better example on how AdaNet works: https://github.com/tensorflow/adanet/blob/master/adanet/exam... Despite being "AutoML", there's still a lot of work that needs to be done to optimize the model. (the second example notebook is a bit better in this aspect: https://github.com/tensorflow/adanet/blob/master/adanet/exam...)

In Introducing AdaNet: Fast and Flexible AutoML with Learning Guarantees