---
title: Barzilai-Borwein Diagonal Quasi-Newton
url: https://www.emergentmind.com/topics/barzilai-borwein-diagonal-type-quasi-newton-method-bb-dqn
type: topic
---

# Barzilai-Borwein Diagonal Quasi-Newton

The Barzilai-Borwein Diagonal-Type Quasi-Newton method (BB-DQN) is a family of algorithms that use diagonal approximations inspired by the Barzilai-Borwein (BB) step-size rules to accelerate large-scale unconstrained optimization, convex composite problems, nonconvex multiobjective programs, and deep network training. The BB-DQN approach leverages iterative secant-like updates to construct diagonal or scalar matrix surrogates for curvature, maintaining low per-iteration cost, robust convergence properties, and empirically strong performance on challenging optimization tasks.

## 1. Mathematical Foundations

BB-DQN methods address optimization problems of the form:
\[
\min_{x \in \mathbb{R}^n} f(x),
\]
or, in multiobjective form,
\[
\min_{x \in \mathbb{R}^n} f(x) = (f_1(x), f_2(x), ..., f_m(x))^\top,
\]
with each $f_i: \mathbb{R}^n \to \mathbb{R}$ continuously differentiable and possibly nonconvex [2512.18348]. The optimality criterion in the multiobjective setting is weak Pareto-optimality: $x^*$ is Pareto-critical if for every direction $d \in \mathbb{R}^n$ there is an index $i$ such that $\nabla f_i(x^*)^T d \ge 0$.

The BB scalar step-size formulas are:
\[
\alpha_k^{\text{BB1}} = \frac{s_k^T s_k}{s_k^T y_k}, \qquad \alpha_k^{\text{BB2}} = \frac{s_k^T y_k}{y_k^T y_k},
\]
with $s_k = x_{k+1} - x_k$, $y_k = \nabla f(x_{k+1}) - \nabla f(x_k)$ [1910.07056, 2205.13711]. Diagonal extensions construct $U^k = \operatorname{diag}(u^k_1, ..., u^k_n)$ by component-wise secant equations, preserving $O(n)$ complexity and reflecting coordinate-wise curvature.

## 2. Algorithmic Structure and Updates

At each iteration, BB-DQN algorithms execute the following core steps:

1. **Shared Diagonal Update:**  
   For multiobjective problems, a single diagonal matrix $B_k = \alpha_k^{-1} I$ is maintained for all objectives [2512.18348]. In convex composite (proximal-gradient) or deep learning settings, each coordinate $u^k_i$ is estimated via:
   \[
   u^k_i = \Pi_{[\beta_1, \beta_2]}\left( \frac{s^k_i y^k_i + \mu u^{k-1}_i}{(s^k_i)^2 + \mu} \right),
   \]
   with projection onto scalar bounds derived from the BB formulas [1910.07056]. For multiobjective settings, descent directions are computed using a weighted sum of gradients, $g_k = \sum_{i=1}^m \lambda_i^k \nabla f_i(x_k)$, where $\lambda^k$ solves a dual minimization over the simplex.

2. **Step-Size Selection and Safeguarding:**  
   Both scalar and diagonal step-sizes are protected by safeguards to ensure positive definiteness and to mitigate erratic variation, particularly under ill-conditioning. Safeguards include:
   \[
   \omega_k = \min\{ c_0, c_1 \|g_k\|^{c_2} \},
   \]
   with $c_0$, $c_1$, $c_2 > 0$ and projection of $\alpha_k$ or $u^k$ into $[\omega_k, \omega_k^{-1}]$ [2512.18348, 1910.07056].

3. **Modified Wolfe Line Search:**  
   Step lengths $t_k$ are determined to satisfy sufficient decrease and curvature criteria on all objectives:
   \[
   f_i(x_k + t_k d_k) \le f_i(x_k) + \sigma_1 t_k \max_j \nabla f_j(x_k)^T d_k,
   \]
   \[
   \max_j \nabla f_j(x_k + t_k d_k)^T d_k \ge \sigma_2 \max_j \nabla f_j(x_k)^T d_k,
   \]
   with $0 < \sigma_1 < \sigma_2 < 1$ [2512.18348].

4. **Proximal Subproblem:**  
   For composite convex problems,
   \[
   x^{k+1} = \operatorname{prox}_{g, U^k}(x^k - (U^k)^{-1} \nabla f(x^k)),
   \]
   enabling efficient, closed-form updates for most regularizers $g$ [1910.07056].

## 3. Theoretical Properties

BB-DQN frameworks admit the following analytical guarantees:

- **Global Convergence:**  
  For multiobjective and composite optimization, if level sets are bounded, gradients are Lipschitz continuous, and the diagonal surrogate matrices are uniformly bounded ($aI \preceq B_k \preceq bI$), the sequence $\{x_k\}$ is well-defined, any accumulation point is Pareto-critical (for multiobjective case), and $\|d_k\| \to 0$ [2512.18348].

- **R-linear Convergence (Strong Convexity):**  
  If all objectives $f_i$ are twice continuously differentiable and satisfy $U I \preceq \nabla^2 f_i(x) \preceq L I$ on the level set, then
  \[
  \|x_{k+1} - x^*\| \le \rho \|x_k - x^*\|,
  \]
  with $\rho = \sqrt{1 - \omega U^2/(2L)} \in (0,1)$ [2512.18348].

- **For Convex Composite Problems:**  
  If $f$ is convex and $L$-smooth and $g$ convex, then global convergence is guaranteed; the gradient mapping norm converges sublinearly ($O(1/k)$) or linearly under strong convexity [1910.07056].

## 4. Practical Applications and Scalability

BB-DQN methods have been deployed in several contexts:

- **Large-scale Nonconvex Multiobjective Problems:**  
  A shared diagonal surrogate dramatically reduces storage from $O(m n^2)$ to $O(n)$ and per-iteration arithmetic from $O(m n^2)$ to $O(m n)$. Comparative experiments show BB-DQN achieves 5–50$\times$ speedups over full quasi-Newton M-BFGSMO on problems with $n = 500$ ($3.4$ms vs $54$ms) and more consistent convergence (lower failure rates) [2512.18348].

- **Ill-conditioned Machine Learning Tasks:**  
  In composite problems (quadratic programs, least-squares, logistic regression, and sparse regularized settings), diagonal BB-based metrics reduce iterations by 15–30% relative to scalar BB PG, and outperform FISTA in certain regimes. For instance, in QP with condition number $10^4$, the method required $16$ iterations versus $22$ for PG(BB) [1910.07056].

- **Deep Learning Optimization:**  
  In deep network training, the BB-DQN-style adaptive step-size (scalar update plugged into Adagrad/RMSprop) yields smoother and sometimes faster training error descent compared to Adam, Adadelta, and fixed decay schedules. On CIFAR-10, BB-Adagrad reduced test error to 20.83% versus 21.85% (Adam), 21.17% (Adadelta), and 24.22% (baseline); ImageNet and MNIST results are competitive or superior in training epochs and generalization [2205.13711].

| Setting        | Storage Cost           | Per-iteration Cost  | Empirical Speed-up      |
|----------------|-----------------------|---------------------|-------------------------|
| Multiobjective | $O(n+m)$ vs $O(m n^2)$| $O(m n)$ vs $O(m n^2)$| $5$–$50\times$ (on $n$ large)|
| Convex PG      | $O(n)$                | $O(n)$              | $15$–$30\%$ fewer its   |
| Deep Networks  | $O(n)$ added          | $O(1)$ per layer    | Smoother, fewer epochs  |

## 5. Connections with Classic Quasi-Newton and Adaptive Methods

The BB-DQN paradigm generalizes classic quasi-Newton and adaptive gradient methods to high dimensions with minimal computational overhead and improved metric adaptation:

- **Quasi-Newton Context:**  
  Standard quasi-Newton methods maintain $n\times n$ Hessian approximations (e.g., BFGS); scalar BB rules use a global curvature estimate. BB-DQN diagonalizes the update, addressing coordinate-wise curvature without incurring $O(n^2)$ cost [1910.07056, 2512.18348].

- **Proximal and Adaptive Methods:**  
  Diagonal BB surrogates can be injected into variable metric proximal gradient iterations. Furthermore, scalar BB-DQN integration into adaptive optimizers (Adagrad, RMSprop) for deep learning exploits the secant approximation to produce layer-wise or coordinate-wise learning rate updates [2205.13711].

- **Safeguarding:**  
  All variants rely on bounding their diagonal surrogates to ensure nondegeneracy and optimize stability under ill-conditioning, with closed-form projection and regularization strategies implemented [1910.07056, 2512.18348].

## 6. Empirical Evaluation and Performance

Comprehensive numerical studies on synthetic benchmarks, machine learning datasets (MNIST, CIFAR, ImageNet), and large multiobjective test instances confirm the principal advantages of BB-DQN:

- **Iteration Count and Runtime:**  
  Diagonal BB-DQN methods consistently reduce iteration counts by up to 27% (for heavily ill-conditioned QPs), with CPU times scaling linearly in $n$ [1910.07056].

- **Reliability and Robustness:**  
  Failure rates (non-convergence over random initializations) are lower or equal relative to competing full-matrix quasi-Newton methods, notably in multiobjective test suites [2512.18348].

- **Generalization in Deep Learning:**  
  When embedded into Adagrad, BB step-sizes yield training error rates competitive with Adam/Adadelta and superior to heuristic decay schedules on deep network tasks, with more stable error trajectories [2205.13711].

## 7. Limitations and Open Directions

The BB-DQN framework does not maintain full curvature information, which in some cases may slow local quadratic convergence compared to full quasi-Newton schemes, especially where off-diagonal Hessian entries are significant. Additionally, theoretical guarantees outside convex or strongly convex regimes rely on safeguarding and line-search conditions.

A plausible implication is that integrating block-diagonal or low-rank modifications may further bridge the gap between classic quasi-Newton performance and BB-DQN scalability. Empirical findings suggest continuing investigation of BB-DQN-based step-size adaptation in deep learning optimizers and highly nonconvex settings.

Source: https://www.emergentmind.com/topics/barzilai-borwein-diagonal-type-quasi-newton-method-bb-dqn