# 1st example given in keyconcepts docs doesn't appear to converge?

**URL:** <https://discuss.ray.io/t/1st-example-given-in-keyconcepts-docs-doesnt-appear-to-converge/365>\
**Category:** Uncategorized\
**Created:** [January 1, 2021, 10:57am UTC](https://discuss.ray.io/t/1st-example-given-in-keyconcepts-docs-doesnt-appear-to-converge/365 "2021-01-01T10:57:15Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![lukeAI](https://avatars.discourse-cdn.com/v4/letter/l/e19adc/32.png) [@lukeAI](https://discuss.ray.io/u/lukeAI)\
**Post date:** [January 1, 2021, 10:57am UTC](https://discuss.ray.io/t/1st-example-given-in-keyconcepts-docs-doesnt-appear-to-converge/365/1 "2021-01-01T10:57:15Z")

</div>

The [first example](https://docs.ray.io/en/master/tune/key-concepts.html#search-algorithms) of a search algorithm given on the introductory Key Concepts page doesn’t appear to work.

The code (comments and imports dropped for clarity) is:

```auto
def objective(x, a, b):
    return a * (x ** 0.5) + b

def trainable(config):
    for x in range(20):
        score = objective(x, config["a"], config["b"])
        tune.report(score=score)

config = {
    "a": tune.uniform(0, 1),
    "b": tune.uniform(0, 20)
}

hyperopt = HyperOptSearch(metric="score", mode="max")

tune.run(
    trainable,
    config=config,
    search_alg=hyperopt,
    num_samples=20,
    stop={"training_iteration": 20}
)

```

I would expect convergence to a=1, b=20, but actually it just looks like the search space is sampled at random for every trial.

- One of the params of [HyperOpt](https://docs.ray.io/en/master/tune/api_docs/suggestion.html#tune-hyperopt) does say `n_initial_points (int) – number of random evaluations of the objective function before starting to aproximate it with tree parzen estimators. Defaults to 20.` which implies that the first 20 trials will be random, but increasing `num_samples` to 100 in `tune.run` still doesn’t seem to lead to convergence.

- limiting concurrency with `ConcurrencyLimiter(hyperopt, max_concurrent=1)` doesn’t seem to make any difference

- If I substitue the `HyperOptSearch` for `BayesOptSearch` AND limit concurrency then I _do_ see convergence.

So I suppose my question is:

- Is this a bug or am I missing something?
- How can HyperOpt be used in a way that will intelligently converge upon optimal hyperparameters?

a sample run of hyperopt from the code above:

 ![hyperopt](https://us1.discourse-cdn.com/flex020/uploads/ray/original/1X/67c5a03a8cc24394cb439c1adfea3c8a7e9fb04b.png)

---

<div class="post-metadata">

**Author:** ![rliaw](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ray.io/rliaw/32/24_2.png) [@rliaw](https://discuss.ray.io/u/rliaw)\
**Post date:** [January 1, 2021, 8:06pm UTC](https://discuss.ray.io/t/1st-example-given-in-keyconcepts-docs-doesnt-appear-to-converge/365/2 "2021-01-01T20:06:41Z")

</div>

Hmm, thanks for typing up this writeup!

I just ran the example, and also pulled up the original hyperopt `fmin` usage: [http://hyperopt.github.io/hyperopt/](http://hyperopt.github.io/hyperopt/)

By setting:

```auto
# Specify the search space and maximize score
hyperopt = HyperOptSearch(metric="score", mode="max")
hyperopt = ConcurrencyLimiter(hyperopt, max_concurrent=1)

# Makes the code run faster for simple functions
# ray.shutdown(); ray.init(local_mode=True)

# Execute 20 trials using HyperOpt and stop after 20 iterations
analysis = tune.run(
    trainable,
    config=config,
    search_alg=hyperopt,
    num_samples=100,
    verbose=1,
    stop={"training_iteration": 20})
    
print(objective(20, **analysis.get_best_config(metric="score", mode="max")))

```

I’m able to get similar results to Hyperopt’s fmin (which also doesn’t seem to converge exactly). So it seems like it’s not an issue with Ray but rather with Hyperopt. Maybe something like this thread may help for Hyperopt? [https://github.com/hyperopt/hyperopt/issues/642](https://github.com/hyperopt/hyperopt/issues/642)

---

<div class="post-metadata">

**Author:** ![lukeAI](https://avatars.discourse-cdn.com/v4/letter/l/e19adc/32.png) [@lukeAI](https://discuss.ray.io/u/lukeAI)\
**Post date:** [January 3, 2021, 2:47pm UTC](https://discuss.ray.io/t/1st-example-given-in-keyconcepts-docs-doesnt-appear-to-converge/365/3 "2021-01-03T14:47:49Z")

</div>

hmm ok. Can I suggest that the given example in the docs be something that works if copied and ran verbatim? It’s quite confusing otherwise.

Possibly this:

```auto
def objective(x, a, b):
    return a * (x ** 0.5) + b

def trainable(config):
    for x in range(20):
        score = objective(x, config["a"], config["b"])
        tune.report(score=score)

config = {
    "a": tune.uniform(0, 1),
    "b": tune.uniform(0, 20)
}

# use a simple naive bayes optimizer
opt = BayesOptSearch(metric="score", mode="max")

# by default, Ray will distribute trials across available computing resources
# naive bayes requires trial results sequentially
opt = ConcurrencyLimiter(opt, max_concurrent=1)

tune.run(
    trainable,
    config=config,
    search_alg=opt,
    num_samples=20,
    stop={"training_iteration": 10}
)

```

---

<div class="post-metadata">

**Author:** ![rliaw](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ray.io/rliaw/32/24_2.png) [@rliaw](https://discuss.ray.io/u/rliaw)\
**Post date:** [January 5, 2021, 5:00am UTC](https://discuss.ray.io/t/1st-example-given-in-keyconcepts-docs-doesnt-appear-to-converge/365/4 "2021-01-05T05:00:08Z")

</div>

Yeah, that’s a good suggestion – thanks for bringing this up. Would you be interested in making an issue/PR?

Happy to help shepherd, just tag @richardliaw!