ResNets Are Deeper Than You Think

• URL: http://arxiv.org/abs/2506.14386v1
• Date: Tue, 17 Jun 2025 10:33:22 GMT
• Title: ResNets Are Deeper Than You Think
• Authors: Christian H. X. Ali Mehmeti-Göpel, Michael Wand,
• Abstract summary: Residual connections remain ubiquitous in modern neural network architectures nearly a decade after their introduction.<n>Their widespread adoption is often credited to their dramatically improved trainability.<n>We show that residual connections confer performance advantages beyond optimization, pointing instead to a deeper inductive bias aligned with the structure of natural data.
• Score: 5.250288418639077
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Residual connections remain ubiquitous in modern neural network architectures nearly a decade after their introduction. Their widespread adoption is often credited to their dramatically improved trainability: residual networks train faster, more stably, and achieve higher accuracy than their feedforward counterparts. While numerous techniques, ranging from improved initialization to advanced learning rate schedules, have been proposed to close the performance gap between residual and feedforward networks, this gap has persisted. In this work, we propose an alternative explanation: residual networks do not merely reparameterize feedforward networks, but instead inhabit a different function space. We design a controlled post-training comparison to isolate generalization performance from trainability; we find that variable-depth architectures, similar to ResNets, consistently outperform fixed-depth networks, even when optimization is unlikely to make a difference. These results suggest that residual connections confer performance advantages beyond optimization, pointing instead to a deeper inductive bias aligned with the structure of natural data.

Related papers

• Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning [57.3885832382455]
  We show that introducing static network sparsity alone can unlock further scaling potential beyond dense counterparts with state-of-the-art architectures.<n>Our analysis reveals that, in contrast to naively scaling up dense DRL networks, such sparse networks achieve both higher parameter efficiency for network expressivity.
  arXiv  Detail & Related papers  (2025-06-20T17:54:24Z)
• Fast Training of Recurrent Neural Networks with Stationary State Feedbacks [48.22082789438538]
  Recurrent neural networks (RNNs) have recently demonstrated strong performance and faster inference than Transformers.<n>We propose a novel method that replaces BPTT with a fixed gradient feedback mechanism.
  arXiv  Detail & Related papers  (2025-03-29T14:45:52Z)
• Power-Enhanced Residual Network for Function Approximation and Physics-Informed Inverse Problems [0.0]
  This paper introduces a novel neural network structure called the Power-Enhancing residual network. It improves the network's capabilities for both smooth and non-smooth functions approximation in 2D and 3D settings. Results emphasize the exceptional accuracy of the proposed Power-Enhancing residual network, particularly for non-smooth functions.
  arXiv  Detail & Related papers  (2023-10-24T10:01:15Z)
• A Generalization of Continuous Relaxation in Structured Pruning [0.3277163122167434]
  Trends indicate that deeper and larger neural networks with an increasing number of parameters achieve higher accuracy than smaller neural networks. We generalize structured pruning with algorithms for network augmentation, pruning, sub-network collapse and removal. The resulting CNN executes efficiently on GPU hardware without computationally expensive sparse matrix operations.
  arXiv  Detail & Related papers  (2023-08-28T14:19:13Z)
• Trainability Preserving Neural Structured Pruning [64.65659982877891]
  We present trainability preserving pruning (TPP), a regularization-based structured pruning method that can effectively maintain trainability during sparsification. TPP can compete with the ground-truth dynamical isometry recovery method on linear networks. It delivers encouraging performance in comparison to many top-performing filter pruning methods.
  arXiv  Detail & Related papers  (2022-07-25T21:15:47Z)
• Multi-Exit Semantic Segmentation Networks [78.44441236864057]
  We propose a framework for converting state-of-the-art segmentation models to MESS networks. specially trained CNNs that employ parametrised early exits along their depth to save during inference on easier samples. We co-optimise the number, placement and architecture of the attached segmentation heads, along with the exit policy, to adapt to the device capabilities and application-specific requirements.
  arXiv  Detail & Related papers  (2021-06-07T11:37:03Z)
• Manifold Regularized Dynamic Network Pruning [102.24146031250034]
  This paper proposes a new paradigm that dynamically removes redundant filters by embedding the manifold information of all instances into the space of pruned networks. The effectiveness of the proposed method is verified on several benchmarks, which shows better performance in terms of both accuracy and computational cost.
  arXiv  Detail & Related papers  (2021-03-10T03:59:03Z)
• Orthogonalized SGD and Nested Architectures for Anytime Neural Networks [30.598394152055338]
  Orthogonalized SGD dynamically re-balances task-specific gradients when training a multitask network. Experiments demonstrate that training with Orthogonalized SGD significantly improves accuracy of anytime networks.
  arXiv  Detail & Related papers  (2020-08-15T03:06:34Z)
• A Differential Game Theoretic Neural Optimizer for Training Residual Networks [29.82841891919951]
  We propose a generalized Differential Dynamic Programming (DDP) neural architecture that accepts both residual connections and convolution layers. The resulting optimal control representation admits a gameoretic perspective, in which training residual networks can be interpreted as cooperative trajectory optimization on state-augmented systems.
  arXiv  Detail & Related papers  (2020-07-17T10:19:17Z)
• Dynamic Hierarchical Mimicking Towards Consistent Optimization Objectives [73.15276998621582]
  We propose a generic feature learning mechanism to advance CNN training with enhanced generalization ability. Partially inspired by DSN, we fork delicately designed side branches from the intermediate layers of a given neural network. Experiments on both category and instance recognition tasks demonstrate the substantial improvements of our proposed method.
  arXiv  Detail & Related papers  (2020-03-24T09:56:13Z)
• Large-Scale Gradient-Free Deep Learning with Recursive Local Representation Alignment [84.57874289554839]
  Training deep neural networks on large-scale datasets requires significant hardware resources. Backpropagation, the workhorse for training these networks, is an inherently sequential process that is difficult to parallelize. We propose a neuro-biologically-plausible alternative to backprop that can be used to train deep networks.
  arXiv  Detail & Related papers  (2020-02-10T16:20:02Z)

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.