Hi, thanks for this repository! So far it works quite well, but now I suddenly encountered a weird error after 11 optimization steps of non-batched HEBO:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
/tmp/ipykernel_2773121/4102601230.py in <module>
35
36 for i in range(opt_steps):
---> 37 rec = opt.suggest()
38 if "bs" in rec:
39 rec["bs"] = 2 ** rec["bs"]
~/.local/lib/python3.8/site-packages/hebo/optimizers/hebo.py in suggest(self, n_suggestions, fix_input)
151 sig = Sigma(model, linear_a = -1.)
152 opt = EvolutionOpt(self.space, acq, pop = 100, iters = 100, verbose = False, es=self.es)
--> 153 rec = opt.optimize(initial_suggest = best_x, fix_input = fix_input).drop_duplicates()
154 rec = rec[self.check_unique(rec)]
155
~/.local/lib/python3.8/site-packages/hebo/acq_optimizers/evolution_optimizer.py in optimize(self, initial_suggest, fix_input, return_pop)
125 crossover = self.get_crossover()
126 algo = get_algorithm(self.es, pop_size = self.pop, sampling = init_pop, mutation = mutation, crossover = crossover, repair = self.repair)
--> 127 res = minimize(prob, algo, ('n_gen', self.iter), verbose = self.verbose)
128 if res.X is not None and not return_pop:
129 opt_x = res.X.reshape(-1, len(lb)).astype(float)
~/.local/lib/python3.8/site-packages/pymoo/optimize.py in minimize(problem, algorithm, termination, copy_algorithm, copy_termination, **kwargs)
81
82 # actually execute the algorithm
---> 83 res = algorithm.run()
84
85 # store the deep copied algorithm in the result object
~/.local/lib/python3.8/site-packages/pymoo/core/algorithm.py in run(self)
211 # while termination criterion not fulfilled
212 while self.has_next():
--> 213 self.next()
214
215 # create the result object to be returned
~/.local/lib/python3.8/site-packages/pymoo/core/algorithm.py in next(self)
231 # call the advance with them after evaluation
232 if infills is not None:
--> 233 self.evaluator.eval(self.problem, infills, algorithm=self)
234 self.advance(infills=infills)
235
~/.local/lib/python3.8/site-packages/pymoo/core/evaluator.py in eval(self, problem, pop, skip_already_evaluated, evaluate_values_of, count_evals, **kwargs)
93 # actually evaluate all solutions using the function that can be overwritten
94 if len(I) > 0:
---> 95 self._eval(problem, pop[I], evaluate_values_of=evaluate_values_of, **kwargs)
96
97 # set the feasibility attribute if cv exists
~/.local/lib/python3.8/site-packages/pymoo/core/evaluator.py in _eval(self, problem, pop, evaluate_values_of, **kwargs)
110 evaluate_values_of = self.evaluate_values_of if evaluate_values_of is None else evaluate_values_of
111
--> 112 out = problem.evaluate(pop.get("X"),
113 return_values_of=evaluate_values_of,
114 return_as_dictionary=True,
~/.local/lib/python3.8/site-packages/pymoo/core/problem.py in evaluate(self, X, return_values_of, return_as_dictionary, *args, **kwargs)
122
123 # do the actual evaluation for the given problem - calls in _evaluate method internally
--> 124 self.do(X, out, *args, **kwargs)
125
126 # make sure the array is 2d before doing the shape check
~/.local/lib/python3.8/site-packages/pymoo/core/problem.py in do(self, X, out, *args, **kwargs)
160
161 def do(self, X, out, *args, **kwargs):
--> 162 self._evaluate(X, out, *args, **kwargs)
163 out_to_2d_ndarray(out)
164
~/.local/lib/python3.8/site-packages/hebo/acq_optimizers/evolution_optimizer.py in _evaluate(self, x, out, *args, **kwargs)
46
47 with torch.no_grad():
---> 48 acq_eval = self.acq(xcont, xenum).numpy().reshape(num_x, self.acq.num_obj + self.acq.num_constr)
49 out['F'] = acq_eval[:, :self.acq.num_obj]
50
~/.local/lib/python3.8/site-packages/hebo/acquisitions/acq.py in __call__(self, x, xe)
37
38 def __call__(self, x : Tensor, xe : Tensor):
---> 39 return self.eval(x, xe)
40
41 class SingleObjectiveAcq(Acquisition):
~/.local/lib/python3.8/site-packages/hebo/acquisitions/acq.py in eval(self, x, xe)
155 normed = ((self.tau - self.eps - py - noise * torch.randn(py.shape)) / ps)
156 dist = Normal(0., 1.)
--> 157 log_phi = dist.log_prob(normed)
158 Phi = dist.cdf(normed)
159 PI = Phi
~/.local/lib/python3.8/site-packages/torch/distributions/normal.py in log_prob(self, value)
71 def log_prob(self, value):
72 if self._validate_args:
---> 73 self._validate_sample(value)
74 # compute the variance
75 var = (self.scale ** 2)
~/.local/lib/python3.8/site-packages/torch/distributions/distribution.py in _validate_sample(self, value)
286 valid = support.check(value)
287 if not valid.all():
--> 288 raise ValueError(
289 "Expected value argument "
290 f"({type(value).__name__} of shape {tuple(value.shape)}) "
ValueError: Expected value argument (Tensor of shape (100, 1)) to be within the support (Real()) of the distribution Normal(loc: 0.0, scale: 1.0), but found invalid values:
tensor([[ -1.1836],
[ -1.2862],
[-11.6360],
[-11.3412],
[ 0.3811],
[ -2.0235],
[ -1.7288],
[ -8.3472],
[-10.1714],
[ -2.6084],
[ -0.8098],
[ -0.9687],
[ -9.0626],
[ -2.2273],
[ -9.0942],
[ -1.6956],
[ -6.6197],
[ -9.3882],
[ -6.1594],
[ -9.2895],
[ -1.7074],
[ 0.8382],
[-14.6693],
[ -0.8303],
[-10.2741],
[ 0.2808],
[ -9.3681],
[ -0.6729],
[ -2.0288],
[ -1.4389],
[ -7.1975],
[-11.5732],
[-10.2751],
[ -1.3800],
[ -1.9773],
[ -1.4668],
[ -9.7166],
[ -8.3093],
[-15.5914],
[ -0.0808],
[ 0.3732],
[-16.2714],
[ -2.3120],
[ -8.7503],
[ -1.6276],
[ nan],
[-15.3692],
[ -9.1615],
[ -9.8093],
[ -2.0716],
[ -1.9259],
[ 0.9543],
[ -8.1521],
[ -2.5709],
[ -1.6153],
[-10.7236],
[ -0.0763],
[ 0.0543],
[ -7.2755],
[-10.6411],
[ -7.9253],
[-19.4996],
[ -2.0001],
[-11.7616],
[-11.0187],
[-12.0727],
[ -1.3243],
[-11.2528],
[ -1.5527],
[ -0.9219],
[ -1.0130],
[-10.1825],
[-18.3420],
[-11.1005],
[ -8.5818],
[-11.1588],
[ -8.8115],
[ -1.0410],
[-15.2722],
[ -1.8399],
[ -1.0827],
[ -1.0277],
[ -6.4768],
[ -8.3902],
[ -0.9513],
[ -1.3429],
[ -1.0889],
[ -7.2952],
[ -7.8548],
[ -0.0231],
[ -7.1898],
[-20.4194],
[ -1.2503],
[-19.6157],
[ -0.3398],
[-15.7221],
[-10.3210],
[ -9.5764],
[ -0.2335],
[ -0.3788]])
Seems like there is a NaN in some distribution of HEBO. But my input parameters (opt.X) and losses (opt.y) are never NaN.
This is the design space I'm using:
space = DesignSpace().parse([{'name': 'lr', 'type' : 'num', 'lb' : 0.00005, 'ub' : 0.1},
{'name': 'n_estimators', 'type' : 'int', 'lb' : 1, 'ub' : 20}, # multiplied by 10
{'name': 'max_depth', 'type' : 'int', 'lb' : 1, 'ub' : 10},
{'name': 'subsample', 'type' : 'num', 'lb' : 0.5, 'ub' : 0.99},
{'name': 'colsample_bytree', 'type' : 'num', 'lb' : 0.5, 'ub' : 0.99},
{'name': 'gamma', 'type' : 'num', 'lb' : 0.01, 'ub' : 10.0},
{'name': 'min_child_weight', 'type' : 'int', 'lb' : 1, 'ub' : 10},
{'name': 'fill_type', 'type' : 'cat', 'categories' : ['median', 'pat_median','pat_ema']},
{'name': 'flat_block_size', 'type' : 'int', 'lb' : 1, 'ub' : 1}
])
opt = HEBO(space)
I already commented out flat_block_size as I thought that maybe it is a problem if lb == ub, but it still crashes.
Any ideas on how I can debug this?
![[Quick Fix] Licence in the Setup ?](https://avatars.githubusercontent.com/u/15108821?v=4)
210 Jan 4, 2023
25.1k Jan 2, 2023
20 Dec 2, 2022
223 Dec 27, 2022
2 Aug 29, 2022
5 Oct 18, 2022
4 Jun 9, 2021
485 Jan 9, 2023
2.2k Jan 3, 2023
7 Feb 10, 2022
1.5k Dec 29, 2022
103 Jul 14, 2022
482 Jan 4, 2023
74 Dec 5, 2022
84 May 11, 2020
127 Dec 12, 2022
342 Dec 2, 2022
2.5k Dec 31, 2022
111 Dec 11, 2022