jboat.fo_ol

Submodules

jboat.fo_ol.meso

class jboat.fo_ol.meso.MESO(ll_objective, lower_loop, ul_model, ul_objective, ll_model, ll_var, ul_var, solver_config)[source]

Bases: DynamicalSystem

Implements the optimization procedure of Moreau Envelope based Single-loop Method (MESO) [1].

Parameters:

ll_objective (Callable) – The lower-level objective of the BLO problem.
ul_objective (Callable) – The upper-level objective of the BLO problem.
ll_model (jittor.Module) – The lower-level model of the BLO problem.
ul_model (jittor.Module) – The upper-level model of the BLO problem.
ll_var (List[jittor.Var]) – The list of lower-level variables of the BLO problem.
ul_var (List[jittor.Var]) – The list of upper-level variables of the BLO problem.
lower_loop (int) – Number of iterations for lower-level optimization.
solver_config (Dict[str, Any]) –
A dictionary containing solver configurations. Expected keys include:
- ”lower_level_opt”: The optimizer for the lower-level model.
- ”MESO” (Dict): A dictionary containing the following keys:
  - ”eta”: Learning rate for the MESO optimization procedure.
  - ”gamma_1”: Regularization parameter for the MESO algorithm.
  - ”c0”: Initial constant for the update steps.
  - ”y_hat_lr”: Learning rate for optimizing the surrogate variable y_hat.

References

[1] Liu R, Liu Z, Yao W, et al. “Moreau Envelope for Nonconvex Bi-Level Optimization: A Single-loop and Hessian-free Solution Strategy,” ICML, 2024.

optimize(ll_feed_dict, ul_feed_dict, current_iter)[source]

Execute the optimization procedure with the data from feed_dict.

Parameters:

ll_feed_dict (Dict) – Dictionary containing the lower-level data used for optimization. It typically includes training data, targets, and other information required to compute the LL objective.
ul_feed_dict (Dict) – Dictionary containing the upper-level data used for optimization. It typically includes validation data, targets, and other information required to compute the UL objective.
current_iter (int) – The current iteration number of the optimization process.

Returns:

A dictionary containing the upper-level objective and the status of hypergradient computation.

Return type:

Dict

jboat.fo_ol.pgdo

class jboat.fo_ol.pgdo.PGDO(ll_objective, lower_loop, ul_model, ul_objective, ll_model, ll_var, ul_var, solver_config)[source]

Bases: DynamicalSystem

Implements the optimization procedure of Penalty-based Gradient Descent Method (PGDO) [1].

Parameters:

ll_objective (Callable) – The lower-level objective of the BLO problem.
ul_objective (Callable) – The upper-level objective of the BLO problem.
ll_model (jittor.Module) – The lower-level model of the BLO problem.
ul_model (jittor.Module) – The upper-level model of the BLO problem.
ll_var (List[jittor.Var]) – The list of lower-level variables of the BLO problem.
ul_var (List[jittor.Var]) – The list of upper-level variables of the BLO problem.
lower_loop (int) – Number of iterations for lower-level optimization.
solver_config (Dict[str, Any]) –
A dictionary containing solver configurations. Expected keys include:
- ”lower_level_opt”: The optimizer for the lower-level model.
- ”PGDO” (Dict): A dictionary containing the following keys:
  - ”y_hat_lr”: Learning rate for optimizing the surrogate variable y_hat.
  - ”gamma_init”: Initial value of the hyperparameter gamma.
  - ”gamma_max”: Maximum value of the hyperparameter gamma.
  - ”gamma_argmax_step”: Step size of the hyperparameter gamma.

References

[1] Shen H, Chen T. “On penalty-based bilevel gradient descent method,” in ICML, 2023.

optimize(ll_feed_dict, ul_feed_dict, current_iter)[source]

Execute the optimization procedure with the data from feed_dict.

Parameters:

ll_feed_dict (Dict) – Dictionary containing the lower-level data used for optimization. It typically includes training data, targets, and other information required to compute the LL objective.
ul_feed_dict (Dict) – Dictionary containing the upper-level data used for optimization. It typically includes validation data, targets, and other information required to compute the UL objective.
current_iter (int) – The current iteration number of the optimization process.

Returns:

A dictionary containing the upper-level objective and the status of hypergradient computation.

Return type:

Dict

jboat.fo_ol.vfo

class jboat.fo_ol.vfo.VFO(ll_objective, lower_loop, ul_model, ul_objective, ll_model, ll_var, ul_var, solver_config)[source]

Bases: DynamicalSystem

Implements the optimization procedure of Value-function based First-Order Method (VFO) [1].

Parameters:

ll_objective (Callable) – The lower-level objective function of the BLO problem.
ul_objective (Callable) – The upper-level objective function of the BLO problem.
ll_model (jittor.Module) – The lower-level model of the BLO problem.
ul_model (jittor.Module) – The upper-level model of the BLO problem.
ll_var (List[jittor.Var]) – A list of lower-level variables of the BLO problem.
ul_var (List[jittor.Var]) – A list of upper-level variables of the BLO problem.
lower_loop (int) – The number of iterations for lower-level optimization.
solver_config (Dict[str, Any]) –
A dictionary containing configurations for the solver. Expected keys include:
- ”lower_level_opt” (jittor.optim.Optimizer): Optimizer for the lower-level model.
- ”VFO” (Dict): Configuration for the VFO algorithm:
  - ”y_hat_lr” (float): Learning rate for optimizing the surrogate variable y_hat.
  - ”eta” (float): Step size for value-function updates.
  - ”u1” (float): Hyperparameter controlling the penalty in the value function.
- ”device” (str): Device on which computations are performed, e.g., “cpu” or “cuda”.

References

[1] R. Liu, X. Liu, X. Yuan, S. Zeng and J. Zhang, “A Value-Function-based: Interior-point Method for Non-convex Bi-level Optimization,” in ICML, 2021.

optimize(ll_feed_dict, ul_feed_dict, current_iter)[source]

Execute the optimization procedure with the data from feed_dict.

Parameters:

ll_feed_dict (Dict) – Dictionary containing the lower-level data used for optimization. It typically includes training data, targets, and other information required to compute the LL objective.
ul_feed_dict (Dict) – Dictionary containing the upper-level data used for optimization. It typically includes validation data, targets, and other information required to compute the UL objective.
current_iter (int) – The current iteration number of the optimization process.

Returns:

A dictionary containing the upper-level objective and the status of hypergradient computation.

Return type:

Dict

jboat.fo_ol.vso

class jboat.fo_ol.vso.VSO(ll_objective, lower_loop, ul_model, ul_objective, ll_model, ll_var, ul_var, solver_config)[source]

Bases: DynamicalSystem

Implements the optimization procedure of Value-function based Sequential Method (VSO) [1].

Parameters:

ll_objective (Callable) – The lower-level objective function of the BLO problem.
ul_objective (Callable) – The upper-level objective function of the BLO problem.
ll_model (jittor.Module) – The lower-level model of the BLO problem.
ul_model (jittor.Module) – The upper-level model of the BLO problem.
ll_var (List[jittor.Var]) – A list of lower-level variables of the BLO problem.
ul_var (List[jittor.Var]) – A list of upper-level variables of the BLO problem.
lower_loop (int) – The number of iterations for lower-level optimization.
solver_config (Dict[str, Any]) –
A dictionary containing configurations for the solver. Expected keys include:
- ”lower_level_opt” (jittor.optim.Optimizer): Optimizer for the lower-level model.
- ”VSO” (Dict): Configuration for the VSO algorithm:
  - ”z_loop” (int): Number of iterations for optimizing the auxiliary variable z.
  - ”ll_l2_reg” (float): L2 regularization coefficient for the lower-level model.
  - ”ul_l2_reg” (float): L2 regularization coefficient for the upper-level model.
  - ”ul_ln_reg” (float): Logarithmic regularization coefficient for the upper-level model.
  - ”reg_decay” (float): Decay rate for the regularization coefficients.
  - ”z_lr” (float): Learning rate for optimizing the auxiliary variable z.
- ”device” (str): Device on which computations are performed, e.g., “cpu” or “cuda”.

References

[1] Liu B, Ye M, Wright S, et al. “BOME! Bilevel Optimization Made Easy: A Simple First-Order Approach,”: in NeurIPS, 2022.

optimize(ll_feed_dict, ul_feed_dict, current_iter)[source]

Execute the optimization procedure with the data from feed_dict.

Parameters:

ll_feed_dict (Dict) – Dictionary containing the lower-level data used for optimization. It typically includes training data, targets, and other information required to compute the LL objective.
ul_feed_dict (Dict) – Dictionary containing the upper-level data used for optimization. It typically includes validation data, targets, and other information required to compute the UL objective.
current_iter (int) – The current iteration number of the optimization process.

Returns:

A dictionary containing the upper-level objective and the status of hypergradient computation.

Return type:

Dict