Spike-timing-dependent Hebbian learning as noisy gradient descent

Hebbian learning is a key principle underlying learning in biological neural networks. It postulates that synaptic changes occur locally, depending on the activities of pre- and postsynaptic neurons. While Hebbian learning based on neuronal firing rates is well explored, much less is known about learning rules that account for precise spike-timing. We relate a Hebbian spike-timing-dependent plasticity rule to noisy gradient descent with respect to a natural loss function on the probability simplex. This connection allows us to prove that the learning rule eventually identifies the presynaptic neuron with the highest activity. We also discover an intrinsic connection to noisy mirror descent.

Negative Stepsizes Make Gradient-Descent-Ascent Converge

Efficient computation of min-max problems is a central question in optimization, learning, games, and controls. Arguably the most natural algorithm is gradient-descent-ascent (GDA). However, since the 1970s, conventional wisdom has argued that GDA fails to converge even on simple problems. This failure spurred an extensive literature on modifying GDA with additional building blocks such as extragradients, optimism, momentum, anchoring, etc. In contrast, we show that GDA converges in its original form by simply using a judicious choice of stepsizes. The key innovation is the proposal of unconventional stepsize schedules (dubbed slingshot stepsize schedules) that are time-varying, asymmetric, and periodically negative. We show that all three properties are necessary for convergence, and that altogether this enables GDA to converge on the classical counterexamples (e.g., unconstrained convex-concave problems). All of our results apply to the last iterate of GDA, as is typically desired in practice. The core algorithmic intuition is that although negative stepsizes make backward progress, they de-synchronize the min and max variables (overcoming the cycling issue of GDA), and lead to a slingshot phenomenon in which the forward progress in the other iterations is overwhelmingly larger. This results in fast overall convergence. Geometrically, the slingshot dynamics leverage the non-reversibility of gradient flow: positive/negative steps cancel to first order, yielding a second-order net movement in a new direction that leads to convergence and is otherwise impossible for GDA to move in. We interpret this as a second-order finite-differencing algorithm and show that, intriguingly, it approximately implements consensus optimization, an empirically popular algorithm for min-max problems involving deep neural networks (e.g., training GANs).

Online Functional Principal Component Analysis on a Multidimensional Domain

Multidimensional functional data streams arise in diverse scientific fields, yet their analysis poses significant challenges. We propose a novel online framework for functional principal component analysis that enables efficient and scalable modeling of such data. Our method represents functional principal components using tensor product splines, enforcing smoothness and orthonormality through a penalized framework on a Stiefel manifold. An efficient Riemannian stochastic gradient descent algorithm is developed, with extensions inspired by adaptive moment estimation and averaging techniques to accelerate convergence. Additionally, a dynamic tuning strategy for smoothing parameter selection is developed based on a rolling averaged block validation score that adapts to the streaming nature of the data. Extensive simulations and real-world applications demonstrate the flexibility and effectiveness of this framework for analyzing multidimensional functional data.

Convergence Properties of Natural Gradient Descent for Minimizing KL Divergence

The Kullback-Leibler (KL) divergence plays a central role in probabilistic machine learning, where it commonly serves as the canonical loss function. Optimization in such settings is often performed over the probability simplex, where the choice of parameterization significantly impacts convergence. In this work, we study the problem of minimizing the KL divergence and analyze the behavior of gradient-based optimization algorithms under two dual coordinate systems within the framework of information geometry$-$ the exponential family ($\theta$ coordinates) and the mixture family ($\eta$ coordinates). We compare Euclidean gradient descent (GD) in these coordinates with the coordinate-invariant natural gradient descent (NGD), where the natural gradient is a Riemannian gradient that incorporates the intrinsic geometry of the parameter space. In continuous time, we prove that the convergence rates of GD in the $\theta$ and $\eta$ coordinates provide lower and upper bounds, respectively, on the convergence rate of NGD. Moreover, under affine reparameterizations of the dual coordinates, the convergence rates of GD in $\eta$ and $\theta$ coordinates can be scaled to $2c$ and $\frac{2}{c}$, respectively, for any $c>0$, while NGD maintains a fixed convergence rate of $2$, remaining invariant to such transformations and sandwiched between them. Although this suggests that NGD may not exhibit uniformly superior convergence in continuous time, we demonstrate that its advantages become pronounced in discrete time, where it achieves faster convergence and greater robustness to noise, outperforming GD. Our analysis hinges on bounding the spectrum and condition number of the Hessian of the KL divergence at the optimum, which coincides with the Fisher information matrix.

NANO-SLAM : Natural Gradient Gaussian Approximation for Vehicle SLAM

Accurate localization is a challenging task for autonomous vehicles, particularly in GPS-denied environments such as urban canyons and tunnels. In these scenarios, simultaneous localization and mapping (SLAM) offers a more robust alternative to GPS-based positioning, enabling vehicles to determine their position using onboard sensors and surrounding environment's landmarks. Among various vehicle SLAM approaches, Rao-Blackwellized particle filter (RBPF) stands out as one of the most widely adopted methods due to its efficient solution with logarithmic complexity relative to the map size. RBPF approximates the posterior distribution of the vehicle pose using a set of Monte Carlo particles through two main steps: sampling and importance weighting. The key to effective sampling lies in solving a distribution that closely approximates the posterior, known as the sampling distribution, to accelerate convergence. Existing methods typically derive this distribution via linearization, which introduces significant approximation errors due to the inherent nonlinearity of the system. To address this limitation, we propose a novel vehicle SLAM method called \textit{N}atural Gr\textit{a}dient Gaussia\textit{n} Appr\textit{o}ximation (NANO)-SLAM, which avoids linearization errors by modeling the sampling distribution as the solution to an optimization problem over Gaussian parameters and solving it using natural gradient descent. This approach improves the accuracy of the sampling distribution and consequently enhances localization performance. Experimental results on the long-distance Sydney Victoria Park vehicle SLAM dataset show that NANO-SLAM achieves over 50\% improvement in localization accuracy compared to the most widely used vehicle SLAM algorithms, with minimal additional computational cost.

How Transformers Learn Regular Language Recognition: A Theoretical Study on Training Dynamics and Implicit Bias

Language recognition tasks are fundamental in natural language processing (NLP) and have been widely used to benchmark the performance of large language models (LLMs). These tasks also play a crucial role in explaining the working mechanisms of transformers. In this work, we focus on two representative tasks in the category of regular language recognition, known as `even pairs' and `parity check', the aim of which is to determine whether the occurrences of certain subsequences in a given sequence are even. Our goal is to explore how a one-layer transformer, consisting of an attention layer followed by a linear layer, learns to solve these tasks by theoretically analyzing its training dynamics under gradient descent. While even pairs can be solved directly by a one-layer transformer, parity check need to be solved by integrating Chain-of-Thought (CoT), either into the inference stage of a transformer well-trained for the even pairs task, or into the training of a one-layer transformer. For both problems, our analysis shows that the joint training of attention and linear layers exhibits two distinct phases. In the first phase, the attention layer grows rapidly, mapping data sequences into separable vectors. In the second phase, the attention layer becomes stable, while the linear layer grows logarithmically and approaches in direction to a max-margin hyperplane that correctly separates the attention layer outputs into positive and negative samples, and the loss decreases at a rate of $O(1/t)$. Our experiments validate those theoretical results.

A mean teacher algorithm for unlearning of language models

One of the goals of language model unlearning is to reduce memorization of selected text instances while retaining the model's general abilities. Despite various proposed methods, reducing memorization of large datasets without noticeable degradation in model utility remains challenging. In this paper, we investigate the mean teacher algorithm (Tarvainen & Valpola, 2017), a simple proximal optimization method from continual learning literature that gradually modifies the teacher model. We show that the mean teacher can approximate a trajectory of a slow natural gradient descent (NGD), which inherently seeks low-curvature updates that are less likely to degrade the model utility. While slow NGD can suffer from vanishing gradients, we introduce a new unlearning loss called "negative log-unlikelihood" (NLUL) that avoids this problem. We show that the combination of mean teacher and NLUL improves some metrics on the MUSE benchmarks (Shi et al., 2024).

Exact Learning Dynamics of In-Context Learning in Linear Transformers and Its Application to Non-Linear Transformers

Transformer models exhibit remarkable in-context learning (ICL), adapting to novel tasks from examples within their context, yet the underlying mechanisms remain largely mysterious. Here, we provide an exact analytical characterization of ICL emergence by deriving the closed-form stochastic gradient descent (SGD) dynamics for a simplified linear transformer performing regression tasks. Our analysis reveals key properties: (1) a natural separation of timescales directly governed by the input data's covariance structure, leading to staged learning; (2) an exact description of how ICL develops, including fixed points corresponding to learned algorithms and conservation laws constraining the dynamics; and (3) surprisingly nonlinear learning behavior despite the model's linearity. We hypothesize this phenomenology extends to non-linear models. To test this, we introduce theory-inspired macroscopic measures (spectral rank dynamics, subspace stability) and use them to provide mechanistic explanations for (1) the sudden emergence of ICL in attention-only networks and (2) delayed generalization (grokking) in modular arithmetic models. Our work offers an exact dynamical model for ICL and theoretically grounded tools for analyzing complex transformer training.

Provable Failure of Language Models in Learning Majority Boolean Logic via Gradient Descent

Recent advancements in Transformer-based architectures have led to impressive breakthroughs in natural language processing tasks, with models such as GPT-4, Claude, and Gemini demonstrating human-level reasoning abilities. However, despite their high performance, concerns remain about the inherent limitations of these models, especially when it comes to learning basic logical functions. While complexity-theoretic analyses indicate that Transformers can represent simple logic functions (e.g., $\mathsf{AND}$, $\mathsf{OR}$, and majority gates) by its nature of belonging to the $\mathsf{TC}^0$ class, these results assume ideal parameter settings and do not account for the constraints imposed by gradient descent-based training methods. In this work, we investigate whether Transformers can truly learn simple majority functions when trained using gradient-based methods. We focus on a simplified variant of the Transformer architecture and consider both $n=\mathrm{poly}(d)$ and $n=\exp(\Omega(d))$ number of training samples, where each sample is a $d$-size binary string paired with the output of a basic majority function. Our analysis demonstrates that even after $\mathrm{poly}(d)$ gradient queries, the generalization error of the Transformer model still remains substantially large, growing exponentially with $d$. This work highlights fundamental optimization challenges in training Transformers for the simplest logical reasoning tasks and provides new insights into their theoretical limitations.

Deep Sturm--Liouville: From Sample-Based to 1D Regularization with Learnable Orthogonal Basis Functions

Although Artificial Neural Networks (ANNs) have achieved remarkable success across various tasks, they still suffer from limited generalization. We hypothesize that this limitation arises from the traditional sample-based (0--dimensionnal) regularization used in ANNs. To overcome this, we introduce \textit{Deep Sturm--Liouville} (DSL), a novel function approximator that enables continuous 1D regularization along field lines in the input space by integrating the Sturm--Liouville Theorem (SLT) into the deep learning framework. DSL defines field lines traversing the input space, along which a Sturm--Liouville problem is solved to generate orthogonal basis functions, enforcing implicit regularization thanks to the desirable properties of SLT. These basis functions are linearly combined to construct the DSL approximator. Both the vector field and basis functions are parameterized by neural networks and learned jointly. We demonstrate that the DSL formulation naturally arises when solving a Rank-1 Parabolic Eigenvalue Problem. DSL is trained efficiently using stochastic gradient descent via implicit differentiation. DSL achieves competitive performance and demonstrate improved sample efficiency on diverse multivariate datasets including high-dimensional image datasets such as MNIST and CIFAR-10.