When Does Margin Clamping Affect Training Variance? Dataset-Dependent Effects in Contrastive Forward-Forward Learning

• URL: http://arxiv.org/abs/2603.00951v1
• Date: Sun, 01 Mar 2026 07:00:38 GMT
• Title: When Does Margin Clamping Affect Training Variance? Dataset-Dependent Effects in Contrastive Forward-Forward Learning
• Abstract summary: Contrastive Forward-Forward (CFF) learning trains Vision Transformers layer by layer against supervised contrastive objectives.<n>We focus on one implementation detail: the positive-pair margin in the contrastive loss is applied through saturating similarity clamping.<n>We prove that an alternative formulation, subtracting the margin after the log-probability, is gradient-neutral under the mean-over-positives reduction.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Contrastive Forward-Forward (CFF) learning trains Vision Transformers layer by layer against supervised contrastive objectives. CFF training can be sensitive to random seed, but the sources of this instability are poorly understood. We focus on one implementation detail: the positive-pair margin in the contrastive loss is applied through saturating similarity clamping, $\min(s + m,\, 1)$. We prove that an alternative formulation, subtracting the margin after the log-probability, is gradient-neutral under the mean-over-positives reduction. On CIFAR-10 ($2 \times 2$ factorial, $n{=}7$ seeds per cell), clamping produces $5.90\times$ higher pooled test-accuracy variance ($p{=}0.003$) with no difference in mean accuracy. Analyses of clamp activation rates, layerwise gradient norms, and a reduced-margin probe point to saturation-driven gradient truncation at early layers. The effect does not transfer cleanly to other datasets: on CIFAR-100, SVHN, and Fashion-MNIST, clamping produces equal or lower variance. Two factors account for the discrepancy. First, positive-pair density per batch controls how often saturation occurs. Second, task difficulty compresses seed-to-seed spread when accuracy is high. An SVHN difficulty sweep confirms the interaction on a single dataset, with the variance ratio moving from $0.25\times$ at high accuracy to $16.73\times$ under aggressive augmentation. In moderate-accuracy regimes with many same-class pairs per batch, switching to the gradient-neutral subtraction reference removes this variance inflation at no cost to mean accuracy. Measuring the layer-0 clamp activation rate serves as a simple check for whether the problem applies.

Related papers

• SMOPD: Selective Token-Entropy Masking for Dirty-History Multi-Turn On-Policy Self-Distillation [0.0]
  We introduce SMOPD (Selective Masking for On-Policy Distillation), a loss-only stabilization method for multi-turn OPSD.<n>For each generated middle-turn reply, SMOPD ranks token positions by student entropy and removes the lowest-entropy 20% from the clipped generalized Jensen-Shannon distillation loss.<n>This design targets token-level uncertainty rather than coarse trajectory outcomes, adds no parameters, and has zero inference-time overhead.
  arXiv  Detail & Related papers  (2026-07-30T08:40:30Z)
• Covariance Last-Layer Ensembles: Function-Space Diversity for Efficient Uncertainty Quantification [0.8803840644459077]
  Cov-LLE restores function-space diversity that weight-orthonormality cannot, and at matched $K$ recovers much of the diversity and calibration of a deep ensemble.<n> Viewing OC as a last-layer ensemble also organizes detectors into a two-axis taxonomy.
  arXiv  Detail & Related papers  (2026-07-26T21:56:02Z)
• From Patches to Trajectories: Privileged Process Supervision for Software-Engineering Agents [56.31499185764872]
  Supervised fine-tuning (SFT) on long teacher trajectories is the dominant way to instill investigation and reasoning in open software-engineering (SWE) agents.<n>We propose Patches-to-Trajectories (P2T), which uses $pstar$ as privileged information during curation and formulates trajectory construction as bi-objective optimization over per-step effectiveness and trajectory length.
  arXiv  Detail & Related papers  (2026-05-21T04:54:55Z)
• Bug or Feature$^2$: Weight Drift, Activation Sparsity and Spikes [53.726365933748134]
  We analyze a negative weight drift induced by the interaction between standard losses and positively biased activation functions.<n>We characterize the sparsity-accuracy tradeoff across 79 configurations and identify a sharp accuracy cliff above $sim$70% activation sparsity.
  arXiv  Detail & Related papers  (2026-05-17T21:29:20Z)
• Correction and Corruption: A Two-Rate View of Error Flow in LLM Protocols [51.56484100374058]
  We propose a paired-outcome measurement interface for auditing a single protocol step on exact-match tasks.<n>For each instance, the interface records a baseline correctness bit and a post-step correctness bit.<n>These rates predict accuracy changes and define a reusable empirical interface testable across seeds, mixtures, and pipelines.
  arXiv  Detail & Related papers  (2026-04-20T13:25:40Z)
• Soft Equivariance Regularization for Invariant Self-Supervised Learning [23.047550451521662]
  Self-supervised learning (SSL) typically learns representations invariant to semantic-preserving augmentations.<n>We propose Soft Equivariance Regularization (SER), a plug-in regularizer that decouples where invariance and equivariance are enforced.<n>SER learns/predicts no per-sample transformation codes/labels, requires no auxiliary transformation-prediction head, and adds only 1.008x training FLOPs.
  arXiv  Detail & Related papers  (2026-03-04T13:36:17Z)
• Optimal Unconstrained Self-Distillation in Ridge Regression: Strict Improvements, Precise Asymptotics, and One-Shot Tuning [61.07540493350384]
  Self-distillation (SD) is the process of retraining a student on a mixture of ground-truth and the teacher's own predictions.<n>We show that for any prediction risk, the optimally mixed student improves upon the ridge teacher for every regularization level.<n>We propose a consistent one-shot tuning method to estimate $star$ without grid search, sample splitting, or refitting.
  arXiv  Detail & Related papers  (2026-02-19T17:21:15Z)
• Information Hidden in Gradients of Regression with Target Noise [2.8911861322232686]
  We show that the gradients alone can reveal the Hessian.<n>We provide non-asymptotic operator-norm guarantees under sub-Gaussian inputs.
  arXiv  Detail & Related papers  (2026-01-26T14:50:16Z)
• Algorithm-Relative Trajectory Valuation in Policy Gradient Control [12.29802562975378]
  We study how trajectory value depends on the learning algorithm in policy-gradient control.<n>Using Trajectory Shapley in an uncertain LQR, we find a negative correlation between Persistence of Excitation (PE) and marginal value under vanilla REINFORCE.
  arXiv  Detail & Related papers  (2025-11-11T06:25:52Z)
• Flip-Flop Consistency: Unsupervised Training for Robustness to Prompt Perturbations in LLMs [2.125148574616104]
  Large Language Models (LLMs) often produce inconsistent answers when faced with different phrasings of the same prompt.<n>We propose Flip-Flop Consistency ($F2C$), an unsupervised training method that improves robustness to such perturbations.<n>We evaluate our method on 11 datasets spanning four NLP tasks, with 4-15 prompt variations per dataset.
  arXiv  Detail & Related papers  (2025-10-16T02:54:01Z)
• Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers [90.50039419576807]
  Reinforcement Learning with Verifiable Rewards (RLVR) trains policies against automated verifiers to avoid costly human labeling.<n>To reduce vulnerability to verifier hacking, many RLVR systems collapse rewards to binary $0,1$ during training.<n>This choice carries a cost: it introduces textitfalse negatives (rejecting correct answers, FNs) and textitfalse positives (accepting incorrect ones, FPs)
  arXiv  Detail & Related papers  (2025-10-01T13:56:44Z)
• Adapt in the Wild: Test-Time Entropy Minimization with Sharpness and Feature Regularization [85.50560211492898]
  Test-time adaptation (TTA) may fail to improve or even harm the model performance when test data have mixed distribution shifts.<n>This is often a key obstacle preventing existing TTA methods from being deployed in the real world.<n>We propose a sharpness-aware and reliable entropy minimization method, called SAR, for stabilizing TTA from two aspects.
  arXiv  Detail & Related papers  (2025-09-05T10:03:00Z)
• Clustered Switchback Designs for Experimentation Under Spatio-temporal Interference [44.644520116360106]
  We estimate the global average treatment effect (GATE), the difference between average outcomes having exposed all units at all times to treatment or to control.<n>We propose a clustered switchback design, where units are grouped into clusters and time steps are grouped into blocks.<n>We show that for graphs that admit good clustering, a truncated Horvitz-Thompson estimator achieves a $tilde O(1/NT)$ mean squared error (MSE)<n>Our results simultaneously generalize the results from citethu2022switchback,ugander2013graph and citetleung2022rate
  arXiv  Detail & Related papers  (2023-12-25T01:00:58Z)
• TIC-TAC: A Framework for Improved Covariance Estimation in Deep Heteroscedastic Regression [109.69084997173196]
  Deepscedastic regression involves jointly optimizing the mean and covariance of the predicted distribution using the negative log-likelihood. Recent works show that this may result in sub-optimal convergence due to the challenges associated with covariance estimation. We study two questions: (1) Does the predicted covariance truly capture the randomness of the predicted mean? Our results show that not only does TIC accurately learn the covariance, it additionally facilitates an improved convergence of the negative log-likelihood.
  arXiv  Detail & Related papers  (2023-10-29T09:54:03Z)
• Gradient Estimation for Binary Latent Variables via Gradient Variance Clipping [6.234350105794441]
  gradient estimation is often necessary for fitting generative models with discrete latent variables. DisARM and other estimators have potentially exploding variance near the boundary of the parameter space. We propose a new gradient estimator textitbitflip-1 that has lower variance at the boundaries of the parameter space.
  arXiv  Detail & Related papers  (2022-08-12T05:37:52Z)
• Understanding Gradient Descent on Edge of Stability in Deep Learning [32.03036040349019]
  This paper mathematically analyzes a new mechanism of implicit regularization in the EoS phase, whereby GD updates due to non-smooth loss landscape turn out to evolve along some deterministic flow on the manifold of minimum loss. The above theoretical results have been corroborated by an experimental study.
  arXiv  Detail & Related papers  (2022-05-19T17:57:01Z)
• Scale-Equivalent Distillation for Semi-Supervised Object Detection [57.59525453301374]
  Recent Semi-Supervised Object Detection (SS-OD) methods are mainly based on self-training, generating hard pseudo-labels by a teacher model on unlabeled data as supervisory signals. We analyze the challenges these methods meet with the empirical experiment results. We introduce a novel approach, Scale-Equivalent Distillation (SED), which is a simple yet effective end-to-end knowledge distillation framework robust to large object size variance and class imbalance.
  arXiv  Detail & Related papers  (2022-03-23T07:33:37Z)
• Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction [63.41789556777387]
  Asynchronous Q-learning aims to learn the optimal action-value function (or Q-function) of a Markov decision process (MDP) We show that the number of samples needed to yield an entrywise $varepsilon$-accurate estimate of the Q-function is at most on the order of $frac1mu_min (1-gamma)5varepsilon2+ fract_mixmu_min (1-gamma)$ up to some logarithmic factor.
  arXiv  Detail & Related papers  (2020-06-04T17:51:00Z)

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.