Identity-Paired Progressive Depth Training: When Trainability Persists Beyond Expressibility

• URL: http://arxiv.org/abs/2607.16800v2
• Date: Wed, 22 Jul 2026 06:46:54 GMT
• Title: Identity-Paired Progressive Depth Training: When Trainability Persists Beyond Expressibility
• Abstract summary: We study emphprogressive depth training (PDT)<n>PDT is a layerwise curriculum that trains a shallow circuit before appending new layers.<n>We show that IP-PDT achieves lower total gate cost than both baselines by eliminating most CNOT gates.
• Score: 11.5521820702581
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Variational Quantum Algorithms (VQAs) are a leading paradigm for near-term quantum computing, yet their training suffers from sensitivity to circuit depth, initialization, and landscape pathologies such as barren plateaus. We study \emph{progressive depth training} (PDT) -- a layerwise curriculum that trains a shallow circuit before appending new layers -- and identify a fundamental obstacle: fixed entangling gates (CNOTs) in hardware-efficient ansätze cause \emph{initialization shock}, an energy spike when new layers are added. We propose \emph{identity-paired progressive depth training} (IP-PDT), which appends forward/inverse block pairs -- each consisting of a standard rotation$+$CNOT block followed by its reverse -- that compose to the identity at initialization. Because the adjacent CNOT rings cancel, the effective circuit retains only \textit{a single entangling layer} surrounded by \textit{overparameterized local rotations}. We prove a simple \textit{Reachable Set Saturation Theorem}: under this construction the variational manifold expands exactly once (when post-entangler rotations are first introduced) and then \emph{saturates}; all subsequent depth increases provide pure overparameterization of single-qubit unitaries. Despite this saturation, progressive addition of rotation parameters can continue to improve optimization outcomes -- a phenomenon we term \emph{trainability beyond expressibility}. We formalize IP-PDT as a continuation method on nested manifolds, prove monotone energy guarantees under an acceptance rule, and connect energy error to ground-state fidelity through spectral-gap inequalities. A detailed resource analysis shows that IP-PDT achieves lower total gate cost than both baselines by eliminating most CNOT gates.

Related papers

• Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior [107.2098567818173]
  Latent Recurrent Transformer (LRT) is a lightweight augmentation of autoregressive transformers.<n>LRT reuses a high-level source-layer hidden state from the previous token as recurrent memory for the next token.
  arXiv  Detail & Related papers  (2026-05-26T10:10:26Z)
• TABES: Trajectory-Aware Backward-on-Entropy Steering for Masked Diffusion Models [35.327100592206115]
  Backward-on-Entropy (BoE) Steering is a gradient-guided inference framework that approximates infinite-horizon context via a single backward pass.<n>To ensure scalability, we introduce ttexttActiveQueryAttention, a sparse adjoint primitive that exploits the structure of the masking objective to reduce backward pass complexity.
  arXiv  Detail & Related papers  (2026-01-30T19:10:32Z)
• Deep Delta Learning [91.75868893250662]
  We introduce Deep Delta Learning (DDL), a novel architecture that generalizes the standard residual connection.<n>We provide a spectral analysis of this operator, demonstrating that the gate $(mathbfX)$ enables dynamic between identity mapping, projection, and geometric reflection.<n>This unification empowers the network to explicitly control the spectrum of its layer-wise transition operator, enabling the modeling of complex, non-monotonic dynamics.
  arXiv  Detail & Related papers  (2026-01-01T18:11:38Z)
• Parallel Diffusion Solver via Residual Dirichlet Policy Optimization [88.7827307535107]
  Diffusion models (DMs) have achieved state-of-the-art generative performance but suffer from high sampling latency due to their sequential denoising nature.<n>Existing solver-based acceleration methods often face significant image quality degradation under a low-dimensional budget.<n>We propose the Ensemble Parallel Direction solver (dubbed as EPD-EPr), a novel ODE solver that mitigates these errors by incorporating multiple gradient parallel evaluations in each step.
  arXiv  Detail & Related papers  (2025-12-28T05:48:55Z)
• Tracing the Representation Geometry of Language Models from Pretraining to Post-training [22.18942718274405]
  We take a spectral approach to investigate the geometry of learned representations across pretraining and post-training.<n>We uncover a consistent non-monotonic sequence of three geometric phases during autoregressive pretraining.<n>Post-training further transforms geometry: SFT and DPO drive "entropy-seeking" dynamics to integrate specific instructional or preferential data.
  arXiv  Detail & Related papers  (2025-09-27T00:46:29Z)
• Description of the Training Process of Neural Networks via Ergodic Theorem : Ghost nodes [3.637162892228131]
  We present a unified framework for understanding and accelerating deep neural networks via training gradient descent (SGD)<n>We introduce a practical diagnostic, the running estimate of the largest Lyapunov exponent, which distinguishes genuine convergence toward stablers.<n>We propose a ghost category extension for standard classifiers that adds auxiliary ghost output nodes so the model gains extra descent directions.
  arXiv  Detail & Related papers  (2025-07-01T17:54:35Z)
• Restarted contractive operators to learn at equilibrium [0.0]
  We introduce an algorithm that combines a restart strategy with JFB computed by AD and we show that the learned steps can be made arbitrarily close to the optimal DEQ framework.<n>We show that this method is effective for training weights in weighted norms; stepsizes and regularization levels of Plug-and-Play schemes; and a DRUNet denoiser embedded in Forward-Backward iterates.
  arXiv  Detail & Related papers  (2025-06-16T08:38:56Z)
• Stable Nonconvex-Nonconcave Training via Linear Interpolation [51.668052890249726]
  This paper presents a theoretical analysis of linearahead as a principled method for stabilizing (large-scale) neural network training. We argue that instabilities in the optimization process are often caused by the nonmonotonicity of the loss landscape and show how linear can help by leveraging the theory of nonexpansive operators.
  arXiv  Detail & Related papers  (2023-10-20T12:45:12Z)
• Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion [83.90492831583997]
  We show that a batch-normalized network can keep the optimal signal propagation properties, but avoid exploding gradients in depth. We use a Multi-Layer Perceptron (MLP) with linear activations and batch-normalization that provably has bounded depth. We also design an activation shaping scheme that empirically achieves the same properties for certain non-linear activations.
  arXiv  Detail & Related papers  (2023-10-03T12:35:02Z)
• Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imaging [142.11622043078867]
  We propose a principled Degradation-Aware Unfolding Framework (DAUF) that estimates parameters from the compressed image and physical mask, and then uses these parameters to control each iteration. By plugging HST into DAUF, we establish the first Transformer-based deep unfolding method, Degradation-Aware Unfolding Half-Shuffle Transformer (DAUHST) for HSI reconstruction.
  arXiv  Detail & Related papers  (2022-05-20T11:37:44Z)
• Deeply Shared Filter Bases for Parameter-Efficient Convolutional Neural Networks [0.0]
  A modern convolutional neural networks (CNNs) have massive identical convolution blocks. In this paper, we show how a filter basis is separated and learned while effectively avoiding the vanishing/exploding gradients problem during training. Experimental results on image classification and object detection show that our approach, unlike previous parameter-sharing approaches, does not trade performance to save parameters.
  arXiv  Detail & Related papers  (2020-06-09T06:09:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.