Error when using bayesian optimization
joeforan76 opened this issue · 5 comments
joeforan76 commented
When using the bayesian optimization algorithm, I get the following error:
ValueError: `f0` passed has more than 1 dimension.
An extract from the output is
Creating new model for trial 6...
INFO:GP:initializing Y
INFO:GP:initializing inference method
INFO:GP:adding kernel and likelihood as parameters
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-9-bd36a65e8a36> in <module>
----> 1 run_study()
<ipython-input-8-768b946e96b2> in run_study()
15 dashboard_port=8877)
16 steps = 3
---> 17 for trial in study:
18 print("-"*100)
19 print(f"Trial:\t{trial.id}\nSteps:\t{steps}\nParameters:{trial.parameters}\n")
~/host/src/sherpa/sherpa/core.py in __next__(self)
377 Allows to write `for trial in study:`.
378 """
--> 379 t = self.get_suggestion()
380 if isinstance(t, Trial):
381 return t
~/host/src/sherpa/sherpa/core.py in get_suggestion(self)
214
215 p = self.algorithm.get_suggestion(self.parameters, self.results,
--> 216 self.lower_is_better)
217 if isinstance(p, dict):
218 self.num_trials += 1
~/host/src/sherpa/sherpa/algorithms/bayesian_optimization.py in get_suggestion(self, parameters, results, lower_is_better)
109
110 domain = self._initialize_domain(parameters)
--> 111 batch = self._generate_bayesopt_batch(X, y, lower_is_better, domain)
112
113 batch_list_of_dicts = self._reverse_to_sherpa_format(batch,
~/host/src/sherpa/sherpa/algorithms/bayesian_optimization.py in _generate_bayesopt_batch(self, X, y, lower_is_better, domain)
142 exact_feval=False,
143 model_type=self.model_type)
--> 144 return bo_step.suggest_next_locations()
145
146 def get_best_pred(self, parameters, results, lower_is_better):
/usr/local/python/lib/python3.6/site-packages/GPyOpt/core/bo.py in suggest_next_locations(self, context, pending_X, ignored_X)
67 self._update_model(self.normalization_type)
68
---> 69 suggested_locations = self._compute_next_evaluations(pending_zipped_X = pending_X, ignored_zipped_X = ignored_X)
70
71 return suggested_locations
/usr/local/python/lib/python3.6/site-packages/GPyOpt/core/bo.py in _compute_next_evaluations(self, pending_zipped_X, ignored_zipped_X)
234
235 ### We zip the value in case there are categorical variables
--> 236 return self.space.zip_inputs(self.evaluator.compute_batch(duplicate_manager=duplicate_manager, context_manager= self.acquisition.optimizer.context_manager))
237
238 def _update_model(self, normalization_type='stats'):
/usr/local/python/lib/python3.6/site-packages/GPyOpt/core/evaluators/batch_local_penalization.py in compute_batch(self, duplicate_manager, context_manager)
35 if self.batch_size >1:
36 # ---------- Approximate the constants of the the method
---> 37 L = estimate_L(self.acquisition.model.model,self.acquisition.space.get_bounds())
38 Min = self.acquisition.model.model.Y.min()
39
/usr/local/python/lib/python3.6/site-packages/GPyOpt/core/evaluators/batch_local_penalization.py in estimate_L(model, bounds, storehistory)
64 pred_samples = df(samples,model,0)
65 x0 = samples[np.argmin(pred_samples)]
---> 66 res = scipy.optimize.minimize(df,x0, method='L-BFGS-B',bounds=bounds, args = (model,x0), options = {'maxiter': 200})
67 minusL = res.fun[0][0]
68 L = -minusL
/usr/local/python/lib/python3.6/site-packages/scipy/optimize/_minimize.py in minimize(fun, x0, args, method, jac, hess, hessp, bounds, constraints, tol, callback, options)
616 elif meth == 'l-bfgs-b':
617 return _minimize_lbfgsb(fun, x0, args, jac, bounds,
--> 618 callback=callback, **options)
619 elif meth == 'tnc':
620 return _minimize_tnc(fun, x0, args, jac, bounds, callback=callback,
/usr/local/python/lib/python3.6/site-packages/scipy/optimize/lbfgsb.py in _minimize_lbfgsb(fun, x0, args, jac, bounds, disp, maxcor, ftol, gtol, eps, maxfun, maxiter, iprint, callback, maxls, finite_diff_rel_step, **unknown_options)
306 sf = _prepare_scalar_function(fun, x0, jac=jac, args=args, epsilon=eps,
307 bounds=new_bounds,
--> 308 finite_diff_rel_step=finite_diff_rel_step)
309
310 func_and_grad = sf.fun_and_grad
/usr/local/python/lib/python3.6/site-packages/scipy/optimize/optimize.py in _prepare_scalar_function(fun, x0, jac, args, bounds, epsilon, finite_diff_rel_step, hess)
260 # calculation reduces overall function evaluations.
261 sf = ScalarFunction(fun, x0, args, grad, hess,
--> 262 finite_diff_rel_step, bounds, epsilon=epsilon)
263
264 return sf
/usr/local/python/lib/python3.6/site-packages/scipy/optimize/_differentiable_functions.py in __init__(self, fun, x0, args, grad, hess, finite_diff_rel_step, finite_diff_bounds, epsilon)
93
94 self._update_grad_impl = update_grad
---> 95 self._update_grad()
96
97 # Hessian Evaluation
/usr/local/python/lib/python3.6/site-packages/scipy/optimize/_differentiable_functions.py in _update_grad(self)
169 def _update_grad(self):
170 if not self.g_updated:
--> 171 self._update_grad_impl()
172 self.g_updated = True
173
/usr/local/python/lib/python3.6/site-packages/scipy/optimize/_differentiable_functions.py in update_grad()
90 self.ngev += 1
91 self.g = approx_derivative(fun_wrapped, self.x, f0=self.f,
---> 92 **finite_diff_options)
93
94 self._update_grad_impl = update_grad
/usr/local/python/lib/python3.6/site-packages/scipy/optimize/_numdiff.py in approx_derivative(fun, x0, method, rel_step, abs_step, f0, bounds, sparsity, as_linear_operator, args, kwargs)
386 f0 = np.atleast_1d(f0)
387 if f0.ndim > 1:
--> 388 raise ValueError("`f0` passed has more than 1 dimension.")
389
390 if np.any((x0 < lb) | (x0 > ub)):
ValueError: `f0` passed has more than 1 dimension.
The relevant portion of my code is as follows
def run_study():
parameters = [
sherpa.Continuous('learning_rate', [1e-6, 1e-1], 'log'),
sherpa.Choice('activation', ['relu', 'tanh', 'logistic']),
sherpa.Continuous('alpha', [1e-7, 0.1], 'log'),
sherpa.Discrete('no_layers', [1, 6]),
sherpa.Continuous('fan_out', [2.0, 4.0])
]
algorithm = sherpa.algorithms.GPyOpt(max_num_trials=150)
study = sherpa.Study(parameters=parameters,
algorithm=algorithm,
lower_is_better=False,
dashboard_port=8877)
steps = 3
for trial in study:
print("-"*100)
print(f"Trial:\t{trial.id}\nSteps:\t{steps}\nParameters:{trial.parameters}\n")
print(f"Creating new model for trial {trial.id}...\n")
# Get hyperparameters
lr = trial.parameters['learning_rate']
act = trial.parameters['activation']
alpha = trial.parameters['alpha']
nl = trial.parameters['no_layers']
f_out = trial.parameters['fan_out']
hidden_layers = get_hidden_layers(nl, f_out)
res = run_trial(data, steps, lr, 1000, alpha, act, hidden_layers)
study.add_observation(trial=trial, iteration=1, objective=res)
study.finalize(trial=trial)
Sherpa commit: 4ad600c71f76a06993464e5078188f552111b851
Python version: 3.6.3
scipy version: 1.5.0
GPyOpt Version: 1.2.6
Is this a bug or am I doing something wrong?
TheVidAllMayThe commented
I'm having the same issue running Bayesian optimization on a xgboost regression. I've used parameter-sherpa in the past for such a problem and it worked fine.
TheVidAllMayThe commented
Seems to be working fine with scipy 1.4.1, so I'm guessing there's some sort of new compatibility issue with scipy 1.5.0+ since they made a few changes to the "optimize" module
belerico commented
Yeah.
Same problem here: I've downgraded to scipy 1.4.1
sherpa-ai commented
Hey @joeforan76, @TheVidAllMayThe, and @belerico, thanks for raising the issue. Build is currently also failing due to this. It looks like GPyOpt hasn't been updated to handle the new API so I will for now set the scipy version as <=1.4.1 in the sherpa requirements. I've created an issue with GPyOpt to make them aware of this