跳到内容

Hyperband 工具集

smac.intensifier.hyperband_utils #

determine_HB #

determine_HB(
    min_budget: float, max_budget: float, eta: int = 3
) -> dict

确定一个 Hyperband 轮次

参数#

min_budget : float 每个试验的最小预算 (保真度单位) max_budget : float 每个试验的最大预算 (保真度单位) eta : int, 默认为 3 控制逐次减半每轮丢弃配置比例的输入。

返回值#

dict 关于 Hyperband 轮次的信息 "max_iterations" "n_configs_in_stage" "budgets_in_stage" "trials_used" "budget_used" "number_of_brackets"

源代码位于 smac/intensifier/hyperband_utils.py 
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
def determine_HB(min_budget: float, max_budget: float, eta: int = 3) -> dict:
    """Determine one Hyperband round

    Parameters
    ----------
    min_budget : float
        Minimum budget per trial in fidelity units
    max_budget : float
        Maximum budget per trial in fidelity units
    eta : int, defaults to 3
        Input that controls the proportion of configurations discarded in each round of Successive Halving.

    Returns
    -------
    dict
        Info about the Hyperband round
            "max_iterations"
            "n_configs_in_stage"
            "budgets_in_stage"
            "trials_used"
            "budget_used"
            "number_of_brackets"

    """
    _s_max = SuccessiveHalving._get_max_iterations(eta, max_budget, min_budget)

    _max_iterations: dict[int, int] = {}
    _n_configs_in_stage: dict[int, list] = {}
    _budgets_in_stage: dict[int, list] = {}

    for i in range(_s_max + 1):
        max_iter = _s_max - i

        _budgets_in_stage[i], _n_configs_in_stage[i] = SuccessiveHalving._compute_configs_and_budgets_for_stages(
            eta, max_budget, max_iter, _s_max
        )
        _max_iterations[i] = max_iter + 1

    total_trials = np.sum([np.sum(v) for v in _n_configs_in_stage.values()])
    total_budget = np.sum([np.sum(v) for v in _budgets_in_stage.values()])

    return {
        "max_iterations": _max_iterations,
        "n_configs_in_stage": _n_configs_in_stage,
        "budgets_in_stage": _budgets_in_stage,
        "trials_used": total_trials,
        "budget_used": total_budget,
        "number_of_brackets": len(_max_iterations),
    }

determine_hyperband_for_multifidelity #

determine_hyperband_for_multifidelity(
    total_budget: float,
    min_budget: float,
    max_budget: float,
    eta: int = 3,
) -> dict

根据总预算确定应该进行多少个 Hyperband 轮次

参数#

total_budget : float 完整优化的总预算 (保真度单位) min_budget : float 每个试验的最小预算 (保真度单位) max_budget : float 每个试验的最大预算 (保真度单位) eta : int, 默认为 3 控制逐次减半每轮丢弃配置比例的输入。

返回值#

dict 关于一个 Hyperband 轮次的信息 "max_iterations" "n_configs_in_stage" "budgets_in_stage" "trials_used" "budget_used" "number_of_brackets" 关于整个优化的信息 "n_trials" "total_budget" "eta" "min_budget" "max_budget"

源代码位于 smac/intensifier/hyperband_utils.py 
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
def determine_hyperband_for_multifidelity(
    total_budget: float, min_budget: float, max_budget: float, eta: int = 3
) -> dict:
    """Determine how many Hyperband rounds should happen based on a total budget

    Parameters
    ----------
    total_budget : float
        Total budget for the complete optimization in fidelity units
    min_budget : float
        Minimum budget per trial in fidelity units
    max_budget : float
        Maximum budget per trial in fidelity units
    eta : int, defaults to 3
        Input that controls the proportion of configurations discarded in each round of Successive Halving.

    Returns
    -------
    dict
        Info about one Hyperband round
            "max_iterations"
            "n_configs_in_stage"
            "budgets_in_stage"
            "trials_used"
            "budget_used"
            "number_of_brackets"
        Info about whole optimization
            "n_trials"
            "total_budget"
            "eta"
            "min_budget"
            "max_budget"

    """
    # Determine the HB
    hyperband_round = determine_HB(eta=eta, min_budget=min_budget, max_budget=max_budget)

    # Calculate how many HB rounds we can have
    budget_used_per_hyperband_round = hyperband_round["budget_used"]
    number_of_full_hb_rounds = int(np.floor(total_budget / budget_used_per_hyperband_round))
    remaining_budget = total_budget % budget_used_per_hyperband_round
    trials_used_per_hb_round = hyperband_round["trials_used"]
    n_configs_in_stage = hyperband_round["n_configs_in_stage"]
    budgets_in_stage = hyperband_round["budgets_in_stage"]

    remaining_trials = 0
    for stage in n_configs_in_stage.keys():
        B = budgets_in_stage[stage]
        C = n_configs_in_stage[stage]
        for b, c in zip(B, C):
            # How many trials are left?
            # If b * c is lower than remaining budget, we can add full c
            # otherwise we need to find out how many trials we can do with this budget
            remaining_trials += min(c, int(np.floor(remaining_budget / b)))
            # We cannot go lower than 0
            # If we are in the case of b*c > remaining_budget, we will not have any
            # budget left. We can not add full c but the number of trials that still fit
            remaining_budget = max(0, remaining_budget - b * c)

    n_trials = int(number_of_full_hb_rounds * trials_used_per_hb_round + remaining_trials)

    hyperband_info = hyperband_round
    hyperband_info["n_trials"] = n_trials
    hyperband_info["total_budget"] = total_budget
    hyperband_info["eta"] = eta
    hyperband_info["min_budget"] = min_budget
    hyperband_info["max_budget"] = max_budget

    return hyperband_info

get_n_trials_for_hyperband_multifidelity #

get_n_trials_for_hyperband_multifidelity(
    total_budget: float,
    min_budget: float,
    max_budget: float,
    eta: int = 3,
    print_summary: bool = True,
) -> int

计算多保真优化所需的试验次数

指定总预算，然后计算这相当于多少个试验。

参数#

total_budget : float 完整优化的总预算 (保真度单位)。一个保真度单位可以是一个 epoch 或数据集大小的一部分。 min_budget : float 每个试验的最小预算 (保真度单位) max_budget : float 每个试验的最大预算 (保真度单位) eta : int, 默认为 3 控制逐次减半每轮丢弃配置比例的输入。

返回值#

int 指定总预算所需的试验次数

源代码位于 smac/intensifier/hyperband_utils.py 
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
def get_n_trials_for_hyperband_multifidelity(
    total_budget: float, min_budget: float, max_budget: float, eta: int = 3, print_summary: bool = True
) -> int:
    """Calculate the number of trials needed for multi-fidelity optimization

    Specify the total budget and find out how many trials that equals.

    Parameters
    ----------
    total_budget : float
        Total budget for the complete optimization in fidelity units.
        A fidelity unit can be one epoch or a fraction of a dataset size.
    min_budget : float
        Minimum budget per trial in fidelity units
    max_budget : float
        Maximum budget per trial in fidelity units
    eta : int, defaults to 3
        Input that controls the proportion of configurations discarded in each round of Successive Halving.

    Returns
    -------
    int
        Number of trials needed for the specified total budgets
    """
    hyperband_info = determine_hyperband_for_multifidelity(
        total_budget=total_budget, eta=eta, min_budget=min_budget, max_budget=max_budget
    )
    if print_summary:
        print_hyperband_summary(hyperband_info=hyperband_info)
    return hyperband_info["n_trials"]

print_hyperband_summary #

print_hyperband_summary(hyperband_info: dict) -> None

打印 MultiFidelityFacade 中使用的 Hyperband 摘要

参数#

hyperband_info : dict 关于 Hyperband 的信息字典

源代码位于 smac/intensifier/hyperband_utils.py 
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
def print_hyperband_summary(hyperband_info: dict) -> None:
    """Print summary about Hyperband as used in the MultiFidelityFacade

    Parameters
    ----------
    hyperband_info : dict
        Info dict about Hyperband
    """
    print("-" * 30, "HYPERBAND IN MULTI-FIDELITY", "-" * 30)
    print("total budget:\t\t", hyperband_info["total_budget"])
    print("total number of trials:\t", hyperband_info["n_trials"])
    print("number of HB rounds:\t", hyperband_info["total_budget"] / hyperband_info["budget_used"])
    print()

    print("\t~~~~~~~~~~~~HYPERBAND ROUND")
    print("\teta:\t\t\t\t\t", hyperband_info["eta"])
    print("\tmin budget per trial:\t\t\t", hyperband_info["min_budget"])
    print("\tmax budget per trial:\t\t\t", hyperband_info["max_budget"])
    print("\ttotal number of trials per HB round:\t", hyperband_info["trials_used"])
    print("\tbudget used per HB round:\t\t", hyperband_info["budget_used"])
    print("\tnumber of brackets:\t\t\t", hyperband_info["number_of_brackets"])
    print("\tbudgets per stage:\t\t\t", hyperband_info["budgets_in_stage"])
    print("\tn configs per stage:\t\t\t", hyperband_info["n_configs_in_stage"])
    print("-" * (2 * 30 + len("HYPERBAND IN MULTI-FIDELITY") + 2))