OmniOpt2

Experiment overview

Setting	Value
Model for non-random steps	BOTORCH_MODULAR
Max. nr. evaluations	500
Number random steps	20
Nr. of workers (parameter)	1

Job Summary per Generation Node

Generation Node	Total	COMPLETED
SOBOL	20	20
BOTORCH_MODULAR	20	20

Formula

\[f(a,b) = \underbrace{a}{\substack{[-1.0,\, 1.0] \in \mathbb{R} \\ \text{continuous}}} - \underbrace{b}{\substack{[-1.0,\, 1.0] \in \mathbb{R} \\ \text{continuous}}}\]

Source

f(a,b) = a - b

ASCII rendering

a - b

Experiment parameters

Name	Type	Lower bound	Upper bound	Type	Log Scale?
a	range	-1000	1000	float	No
b	range	-1000	1000	float	No

Number of evaluations

Failed	Succeeded	Running	Total
0	40	0	40

Result names and types

name	min/max
RESULT	min

Git-Version

Commit: a4dcaccab0930450937d7d4d382f65572a51addd (9970-22-ga4dcaccab)

Arguments Overview

Key	Value
install	False
config_yaml	None
config_toml	None
config_json	None
num_random_steps	20
max_eval	500
run_program	[['OMNIOPT_PARAM_a=%a', 'OMNIOPT_PARAM_b=%b', '/home/norman/.omniax_venvs/Python_3.13.5/x86_64/bin/python',
	'/home/norman/repos/OmniOpt/runs/a/2/run_with_formula.py']]
experiment_name	a
mem_gb	10
parameter	[['a', 'range', '-1000', '1000', 'float', 'false'], ['b', 'range', '-1000', '1000', 'float', 'false']]
continue_previous_job	None
experiment_constraints	None
run_dir	runs
seed	None
verbose_tqdm	False
model	BOTORCH_MODULAR
gridsearch	False
occ	False
show_sixel_scatter	False
show_sixel_general	False
show_sixel_trial_index_result	False
follow	True
wait_until_ended	False
send_anonymized_usage_stats	True
ui_url	None
root_venv_dir	/home/norman
exclude	None
main_process_gb	8
max_nr_of_zero_results	50
abbreviate_job_names	False
orchestrator_file	None
checkout_to_latest_tested_version	False
live_share	True
disable_tqdm	False
local_cpu_monitor	False
disable_previous_job_constraint	False
workdir
occ_type	euclid
result_names	['RESULT=min']
minkowski_p	2
signed_weighted_euclidean_weights
generation_strategy	None
generate_all_jobs_at_once	True
revert_to_random_when_seemingly_exhausted	True
load_data_from_existing_jobs	[]
n_estimators_randomforest	100
max_attempts_for_generation	20
external_generator	None
optuna_sampler	None
optuna_pruner	none
optuna_n_startup_trials	10
optuna_multivariate	False
optuna_group	False
optuna_constraints	False
optuna_n_ei_candidates	0
optuna_storage	None
optuna_study_name	omniopt_study
optuna_no_load_if_exists	False
optuna_extra_iters	1
username	None
max_failed_jobs	0
num_cpus_main_job	None
calculate_pareto_front_of_job	[]
show_generate_time_table	False
force_choice_for_ranges	False
max_abandoned_retrial	20
share_password	None
dryrun	False
db_url	None
run_program_once	None
worker_generator_path	None
save_to_database	False
range_max_difference	1000000
skip_search	False
nr_evals_per_arm	1
dump_config	None
formula	f(a,b) = a - b
formula_mode	auto
formula_python_path	/home/norman/.omniax_venvs/Python_3.13.5/x86_64/bin/python
dont_warm_start_refitting	False
refit_on_cv	False
fit_out_of_design	False
fit_abandoned	False
dont_jit_compile	False
num_restarts	20
raw_samples	1024
max_num_of_parallel_sruns	16
no_transform_inputs	False
no_normalize_y	False
transforms	[]
number_of_generators	1
num_parallel_jobs	1
worker_timeout	60
slurm_use_srun	False
time	60
partition	alpha
reservation	None
force_local_execution	False
slurm_signal_delay_s	0
nodes_per_job	1
cpus_per_task	1
account	None
gpus	1
dependency	None
run_mode	local
verbose	False
verbose_break_run_search_table	False
debug	False
flame_graph	False
memray	False
no_sleep	False
tests	False
show_worker_percentage_table_at_end	False
auto_exclude_defective_hosts	False
run_tests_that_fail_on_taurus	False
raise_in_eval	False
show_ram_every_n_seconds	0
show_generation_and_submission_sixel	False
just_return_defaults	False
prettyprint	False
runtime_debug	False
debug_stack_regex
debug_stack_trace_regex	None
show_func_name	False
beartype	False

This logs the CPU and RAM usage of the main worker process.

timestamp,ram_usage_mb,cpu_usage_percent
1788803895,892.625,62.1
1788803989,903.92578125,58
1788804058,906,36.9
1788804128,907.66015625,43.3
1788804192,907.84765625,65.7
1788804256,926.6328125,69.9
1788804318,927.71484375,55
1788804397,928.88671875,82.9
1788804465,929.953125,80.3
1788804531,930.84765625,65.4
1788804597,932.3515625,57.7
1788804669,933.94921875,62.4
1788804736,941.0703125,49.3
1788804800,941.8125,31.3
1788804866,942.01953125,43.2
1788804936,942.20703125,51.5

`RESULT` (goal: minimize)

Best value: -2000
Achieved at:
- b = 1000 (r=-0.759, strong negative correlation)
- a = -1000 (r=0.743, strong positive correlation)
- run_time = 6 (r=-0.241, weak negative correlation)

Top-5 Best Results

Parameter Sensitivity Ranking

Parameters ranked by absolute Pearson correlation with each result. Stronger correlations (|r| ≥ 0.7) suggest the parameter has more influence on the outcome.

Convergence Analysis

Parameter statistics

Parameter	Min	Max	Mean	Std Dev	Count
run_time	6	7	6.05	0.2179	40
RESULT	-2000	1542.3414	-95.6455	891.5473	40
a	-1000	991.3032	-45.7285	585.6707	40
b	-998.0823	1000	49.9169	601.309	40