Open Problems

Deep Learning Theory & Optimization Dynamics

Bridging the Activation Divide in Neural Network Optimization Dynamics Theory

Barrier to removePartly addressed
Possible candidate · 2/5 runs13 papers report this38% from 2025+

Generated automatically from the limitations stated in 13 papers (NeurIPS, ICML, ICLR), listed under Evidence. It is not a paper, and it does not come from papers submitted to CSPaper.

The problem

Current theoretical analyses of neural network training dynamics are split across incompatible mathematical preconditions: one major body of literature strictly requires high-order smoothness ($C^2$, $C^\infty$, bounded derivatives, or odd symmetry), which explicitly excludes standard piecewise-linear activations like ReLU, while another body relies strictly on piecewise linearity and positive homogeneity, failing to transfer to smooth activations like GELU, SiLU, or tanh. As a result, foundational theoretical predictions—such as edge-of-stability behavior, width-independent convergence rates, and representation learning bounds—cannot be generalized across activation families. Without analytical tools that either handle subgradient boundary crossings or bound the divergence between smooth approximations and exact piecewise-linear trajectories during training, optimization theory remains fragmented into mutually exclusive activation regimes.

Why it matters

Enables optimization and generalization theorems developed exclusively for smooth activations to be transferred rigorously to ReLU networks (and vice versa). It also establishes explicit mathematical boundaries for when smooth approximations faithfully represent non-smooth neural network training dynamics.

Ways to approach it

Prior-work checks are free with an account. Results someone already ran are shown to everyone.

  1. 1

    Trajectory-Dependent Smoothing Error Bounds: Analyze the discrepancy between gradient descent trajectories on exact piecewise-linear networks and parameterized smooth approximations (e.g., smoothed ReLU$_\iota$ or GELU), measuring the cumulative error and iteration complexity penalty as a function of the smoothing scale $\iota$ and the rate of neuron activation-state transitions.

  2. 2

    Differential Inclusions vs. Regularized Gradient Flows: Formulate neural network training dynamics using Clarke subdifferentials and compare the resulting non-smooth flow directly against the zero-temperature limit of smooth ODE dynamics, measuring convergence rate bounds and stability thresholds on synthetic two-layer networks.

  3. 3

    Unified Weak-Smoothness Lyapunov Framework: Construct Lyapunov functionals for gradient descent dynamics that replace strict $C^2$ requirements with directional or almost-everywhere differentiability, measuring whether width-independent convergence guarantees hold across ReLU, LeakyReLU, and smooth activations under identical optimizer settings.

Have a different approach?

Describe how you would tackle this problem and we'll look for papers that already do it. Free; your text stays private.

Free · 3 checks per day

Why it might fail

If gradient descent dynamics for ReLU networks exhibit pathological activation-switching behavior that causes smooth surrogate trajectories to diverge exponentially rather than polynomially over training time. Additionally, technical barriers in non-smooth dynamical systems (differential inclusions) may prevent closing the gap without introducing equally restrictive geometric assumptions.

Evidence

Each paper's own statement of the limitation, verbatim.

Show all 13 papers

Nearest existing work

Related open problems

Deep Learning Theory & Optimization Dynamics

Scope to testPartly addressed

Extending Two-Layer Network Theory to Deep and Structured Architectures

A substantial body of rigorous results—on training dynamics, predictor statistics, generalization, and under-fitting—is proven only for one- or two-layer fully-connected networks, often with fixed or special activations. Practitioners use deep residual, convolutional, and attention models, so none of these guarantees can be checked against the systems that matter. Until the theory carries over, each paper's conclusions remain unvalidated in practice, and the specific mechanisms they identify may be artifacts of the shallow, unstructured setting.

Weak candidate · 1/4 runs8 papers report this40% from 2025+

Deep Learning Theory & Optimization Dynamics

Scope to testPartly addressed

Cross-Architecture Empirical Validation of Deep Learning Theory Predictors

Theoretical analysis and optimization dynamic guarantees in deep learning are overwhelmingly developed and proved on shallow fully connected ReLU models or two-layer networks. As a result, theoretical claims regarding convergence rates, generalization bounds, and optimization statistics are rarely verified on non-feedforward or deeper architectures such as CNNs, ResNets, and Transformers. Without systematic empirical evaluation across these structural settings, it remains unknown whether these theoretical quantities correlate with actual training dynamics or are merely artifacts of idealized shallow feedforward assumptions.

Weak candidate · 1/4 runs6 papers report this17% from 2025+

Deep Learning Theory & Optimization Dynamics

Effect to explainOpen

Empirical Benchmarking of Generalization Failure in Alternative Optimization Dynamics

Alternative optimization methods, such as exact Gauss-Newton (GN) and non-backpropagation dynamics (e.g., NMNC), exhibit severe generalization gaps and early loss saturation when scaled to deep networks and mini-batch settings. Standard regularizers (dropout, weight decay, data augmentation, pseudoinverse regularization) and initialization heuristics developed on shallow models consistently fail to close these train-test gaps. Without a controlled comparative evaluation across these distinct settings, it remains unknown whether these generalization failures share common optimization dynamics or require fundamentally different stabilization interventions.

Possible candidate · 3/5 runs3 papers report this67% from 2025+
Generated automatically, not curated by hand. Automated prior-work checks catch about a third of existing work, so treat this problem as a lead to investigate.