arXiv subjects

Binchuan Qi

Publications and source records attributed to Binchuan Qi.

6 recordsLinked to original sources

arXiv2026

Generalized Convexity and Smoothness via Conjugate Duality: Optimization Theory for Deep Neural Networks

Deep neural network (DNN) training with stochastic gradient descent (SGD) and its variants achieves strong empirical performance, yet classical optimization theory does not fully explain this success. This limitation arises because conventional analyses rely on assumptions such as differentiability, convexity, or smoothness, which are often violated by DNN objectives. In this paper, we establish a unified optimization framework for DNN training by generalizing classical convexity and smoothness through Legendre functions and convex conjugation. Specifically, we introduce $\mathcal{H}(ψ)$-convexity and $\mathcal{H}(Ψ)$-smoothness, which unify convex and non-convex as well as smooth and non-smooth objectives within a single formalism and reveal a natural duality between generalized smoothness and convexity. Building on these generalized properties, we introduce generalized gradient descent (GD) and generalized SGD through convex conjugation. We theoretically prove that generalized GD admits an optimal learning rate of exactly $1$, and derive rigorous gradient-energy-based convergence rates for both proposed optimizers. We further reformulate DNN training as a composite optimization problem, demonstrating that its convergence relies on jointly reducing the gradient energy and controlling the induced norm of the network Jacobian. To characterize the practical influences of network architectures and training configurations, we introduce the gradient correlation factor and model capacity risk, and quantitatively analyze how architectural designs, batch size, and model capacity shape training convergence. Extensive experiments across diverse network architectures, datasets, optimizers, and loss functions validate our theoretical bounds and demonstrate precise alignment between our theoretical predictions and empirical training dynamics.

cs.LG↗

arXiv2026

Conjugate Learning Theory: Uncovering the Mechanisms of Trainability and Generalization in Deep Neural Networks

In this work, we propose a notion of practical learnability grounded in finite sample settings, and develop a conjugate learning theoretical framework based on convex conjugate duality to characterize this learnability property. Building on this foundation, we demonstrate that training deep neural networks (DNNs) with mini-batch stochastic gradient descent (SGD) achieves global optima of empirical risk by jointly controlling the extreme eigenvalues of a structure matrix and the gradient energy, and we establish a corresponding convergence theorem. We further elucidate the impact of batch size and model architecture (including depth, parameter count, sparsity, skip connections, and other characteristics) on non-convex optimization. Additionally, we derive a model-agnostic lower bound for the achievable empirical risk, theoretically demonstrating that data determines the fundamental limit of trainability. On the generalization front, we derive deterministic and probabilistic bounds on generalization error based on generalized conditional entropy measures. The former explicitly delineates the range of generalization error, while the latter characterizes the distribution of generalization error relative to the deterministic bounds under independent and identically distributed (i.i.d.) sampling conditions. Furthermore, these bounds explicitly quantify the influence of three key factors: (i) information loss induced by irreversibility in the model, (ii) the maximum attainable loss value, and (iii) the generalized conditional entropy of features with respect to labels. Moreover, they offer a unified theoretical lens for understanding the roles of regularization, irreversible transformations, and network depth in shaping the generalization behavior of deep neural networks. Extensive experiments validate all theoretical predictions, confirming the framework's correctness and consistency.

stat.ML↗

arXiv2025

Probability Distribution Learning and Its Application in Deep Learning

Despite its empirical success, deep learning still lacks a comprehensive theoretical understanding of model fitting and generalization. This paper proposes the probability distribution (PD) learning framework to analyze the optimization and generalization mechanisms of deep learning. Within this framework, the conditional distribution of labels given features is the primary learning target, with the loss function, prior knowledge, and model properties explicitly characterized. Under these formulations, we establish theoretical guarantees on optimizability, even in non-convex settings, and derive generalization error bounds that provide meaningful explanations for practical performance. Specifically, we first prove theoretically that the Fenchel-Young loss is the natural and necessary choice for solving PD learning problems, thereby justifying the generality of conclusions based on this loss. Second, to capture the characteristics of deep neural networks (DNNs), we introduce the notions of $\mathcal{H}(ψ)$-convexity and $\mathcal{H}(Ψ)$-smoothness, which generalize the classical concepts of strong convexity and Lipschitz smoothness. Based on them, we provide a theoretical explanation for the effectiveness of SGD in training DNNs. Finally, we derive model-independent bounds on the expected risk and generalization error for trained models, revealing the influence of the training set size, regularization term, the mutual information between labels and features, and the information loss caused by model irreversibility on risk and generalization. Based on our theoretical analysis and experimental validation, we believe that the PD learning framework facilitates a deeper and more unified theoretical understanding of deep learning.

cs.LG↗

arXiv2025

Extended convexity and smoothness and their applications in deep learning

Classical assumptions like strong convexity and Lipschitz smoothness often fail to capture the nature of deep learning optimization problems, which are typically non-convex and non-smooth, making traditional analyses less applicable. This study aims to elucidate the mechanisms of non-convex optimization in deep learning by extending the conventional notions of strong convexity and Lipschitz smoothness. By leveraging these concepts, we prove that, under the established constraints, the empirical risk minimization problem is equivalent to optimizing the local gradient norm and structural error, which together constitute the upper and lower bounds of the empirical risk. Furthermore, our analysis demonstrates that the stochastic gradient descent (SGD) algorithm can effectively minimize the local gradient norm. Additionally, techniques like skip connections, over-parameterization, and random parameter initialization are shown to help control the structural error. Ultimately, we validate the core conclusions of this paper through extensive experiments. Theoretical analysis and experimental results indicate that our findings provide new insights into the mechanisms of non-convex optimization in deep learning.

cs.LG↗

arXiv2025

Towards Understanding the Optimization Mechanisms in Deep Learning

In this paper, we adopt a probability distribution estimation perspective to explore the optimization mechanisms of supervised classification using deep neural networks. We demonstrate that, when employing the Fenchel-Young loss, despite the non-convex nature of the fitting error with respect to the model's parameters, global optimal solutions can be approximated by simultaneously minimizing both the gradient norm and the structural error. The former can be controlled through gradient descent algorithms. For the latter, we prove that it can be managed by increasing the number of parameters and ensuring parameter independence, thereby providing theoretical insights into mechanisms such as over-parameterization and random initialization. Ultimately, the paper validates the key conclusions of the proposed method through empirical results, illustrating its practical effectiveness.

cs.LG↗

arXiv2024

Error Bounds of Supervised Classification from Information-Theoretic Perspective

In this paper, we explore bounds on the expected risk when using deep neural networks for supervised classification from an information theoretic perspective. Firstly, we introduce model risk and fitting error, which are derived from further decomposing the empirical risk. Model risk represents the expected value of the loss under the model's predicted probabilities and is exclusively dependent on the model. Fitting error measures the disparity between the empirical risk and model risk. Then, we derive the upper bound on fitting error, which links the back-propagated gradient and the model's parameter count with the fitting error. Furthermore, we demonstrate that the generalization errors are bounded by the classification uncertainty, which is characterized by both the smoothness of the distribution and the sample size. Based on the bounds on fitting error and generalization, by utilizing the triangle inequality, we establish an upper bound on the expected risk. This bound is applied to provide theoretical explanations for overparameterization, non-convex optimization and flat minima in deep learning. Finally, empirical verification confirms a significant positive correlation between the derived theoretical bounds and the practical expected risk, thereby affirming the practical relevance of the theoretical findings.

cs.LG↗