SIAM Conference on Mathematics of Data Science (MDS26)
Researchers and practitioners will discuss mathematical foundations of data science, including high-dimensional geometry, dimensionality reduction, scalable algorithms, uncertainty and machine learning. The conference takes place in person at the Salt Palace Convention Center on 16–20 November 2026. Registration is open, with early rates through 19 October; abstract and travel-support deadlines have passed. Registration also covers the co-located SIAM Imaging Science and Data Mining conferences.
Maintaining Plasticity in Neural Networks
Nonstationarity presents a variety of challenges for machine learning systems. One surprising pathology which can arise in nonstationary learning problems is plasticity loss, whereby making progress on new learning objectives becomes more difficult as training progresses. Networks which are unable to adapt in response to changes in their environment experience plateaus or even declines in performance in highly non-stationary domains such as reinforcement learning, where the learner must quickly adapt to new information even after hundreds of millions of optimization steps. The loss of plasticity manifests in a cluster of related empirical phenomena which have been identified by a number of recent works, including the primacy bias, implicit under-parameterization, rank collapse, and capacity loss. While this phenomenon is widely observed, it is still not fully understood. This talk will present exciting recent results which shed light on the mechanisms driving the loss of plasticity in a variety of learning problems and survey methods to maintain network plasticity in non-stationary tasks, with a particular focus on deep reinforcement learning.
A Better Method to Quantify Perceptual Thresholds : Parameter-free, Model-free, Adaptive procedures
The ‘quantification’ of perception is arguably both one of the most important and most difficult aspects of perception study. This is particularly true in visual perception, in which the evaluation of the perceptual threshold is a pillar of the experimental process. The choice of the correct adaptive psychometric procedure, as well as the selection of the proper parameters, is a difficult but key aspect of the experimental protocol. For instance, Bayesian methods such as QUEST, require the a priori choice of a family of functions (e.g. Gaussian), which is rarely known before the experiment, as well as the specification of multiple parameters. Importantly, the choice of an ill-fitted function or parameters will induce costly mistakes and errors in the experimental process. In this talk we discuss the existing methods and introduce a new adaptive procedure to solve this problem, named, ZOOM (Zooming Optimistic Optimization of Models), based on recent advances in optimization and statistical learning. Compared to existing approaches, ZOOM is completely parameter free and model-free, i.e. can be applied on any arbitrary psychometric problem. Moreover, ZOOM parameters are self-tuned, thus do not need to be manually chosen using heuristics (eg. step size in the Staircase method), preventing further errors. Finally, ZOOM is based on state-of-the-art optimization theory, providing strong mathematical guarantees that are missing from many of its alternatives, while being the most accurate and robust in real life conditions. In our experiments and simulations, ZOOM was found to be significantly better than its alternative, in particular for difficult psychometric functions or when the parameters when not properly chosen. ZOOM is open source, and its implementation is freely available on the web. Given these advantages and its ease of use, we argue that ZOOM can improve the process of many psychophysics experiments.
Optimization at the Single Neuron Level: Prediction of Spike Sequences and Emergence of Synaptic Plasticity Mechanisms
Intelligent behavior depends on the brain’s ability to anticipate future events. However, the learning rules that enable neurons to predict and fire ahead of sensory inputs remain largely unknown. We propose a plasticity rule based on pre-dictive processing, where the neuron learns a low-rank model of the synaptic input dynamics in its membrane potential. Neurons thereby amplify those synapses that maximally predict other synaptic inputs based on their temporal relations, which provide a solution to an optimization problem that can be implemented at the single-neuron level using only local information. Consequently, neurons learn sequences over long timescales and shift their spikes towards the first inputs in a sequence. We show that this mechanism can explain the development of anticipatory motion signaling and recall in the visual system. Furthermore, we demonstrate that the learning rule gives rise to several experimentally observed STDP (spike-timing-dependent plasticity) mechanisms. These findings suggest prediction as a guiding principle to orchestrate learning and synaptic plasticity in single neurons.
Event-based Backpropagation for Exact Gradients in Spiking Neural Networks
Gradient-based optimization powered by the backpropagation algorithm proved to be the pivotal method in the training of non-spiking artificial neural networks. At the same time, spiking neural networks hold the promise for efficient processing of real-world sensory data by communicating using discrete events in continuous time. We derive the backpropagation algorithm for a recurrent network of spiking (leaky integrate-and-fire) neurons with hard thresholds and show that the backward dynamics amount to an event-based backpropagation of errors through time. Our derivation uses the jump conditions for partial derivatives at state discontinuities found by applying the implicit function theorem, allowing us to avoid approximations or substitutions. We find that the gradient exists and is finite almost everywhere in weight space, up to the null set where a membrane potential is precisely tangent to the threshold. Our presented algorithm, EventProp, computes the exact gradient with respect to a general loss function based on spike times and membrane potentials. Crucially, the algorithm allows for an event-based communication scheme in the backward phase, retaining the potential advantages of temporal sparsity afforded by spiking neural networks. We demonstrate the optimization of spiking networks using gradients computed via EventProp and the Yin-Yang and MNIST datasets with either a spike time-based or voltage-based loss function and report competitive performance. Our work supports the rigorous study of gradient-based optimization in spiking neural networks as well as the development of event-based neuromorphic architectures for the efficient training of spiking neural networks. While we consider the leaky integrate-and-fire model in this work, our methodology generalises to any neuron model defined as a hybrid dynamical system.
Optimal initialization strategies for Deep Spiking Neural Networks
Recent advances in neuromorphic hardware and Surrogate Gradient (SG) learning highlight the potential of Spiking Neural Networks (SNNs) for energy-efficient signal processing and learning. Like in Artificial Neural Networks (ANNs), training performance in SNNs strongly depends on the initialization of synaptic and neuronal parameters. While there are established methods of initializing deep ANNs for high performance, effective strategies for optimal SNN initialization are lacking. Here, we address this gap and propose flexible data-dependent initialization strategies for SNNs.
Optimising spiking interneuron circuits for compartment-specific feedback
Cortical circuits process information by rich recurrent interactions between excitatory neurons and inhibitory interneurons. One of the prime functions of interneurons is to stabilize the circuit by feedback inhibition, but the level of specificity on which inhibitory feedback operates is not fully resolved. We hypothesized that inhibitory circuits could enable separate feedback control loops for different synaptic input streams, by means of specific feedback inhibition to different neuronal compartments. To investigate this hypothesis, we adopted an optimization approach. Leveraging recent advances in training spiking network models, we optimized the connectivity and short-term plasticity of interneuron circuits for compartment-specific feedback inhibition onto pyramidal neurons. Over the course of the optimization, the interneurons diversified into two classes that resembled parvalbumin (PV) and somatostatin (SST) expressing interneurons. The resulting circuit can be understood as a neural decoder that inverts the nonlinear biophysical computations performed within the pyramidal cells. Our model provides a proof of concept for studying structure-function relations in cortical circuits by a combination of gradient-based optimization and biologically plausible phenomenological models
Exploring the evolution of motile curved bacteria using a regularized Stokeslet Boundary Element Method and Pareto optimality theory
Bacteria exhibit a bewildering diversity of morphologies, but despite their impact on nearly all aspects of life, they are frequently classified into a few general categories, usually just “spheres” and “rods.” Curved-rod bacteria are one simple variation observed in many environments, particularly the ocean. However, why so many species have evolved this shape is unknown. We used a regularized Stokeslet Boundary Element Method to model the motility of flagellated, curved bacteria. We show that curvature can increase swimming efficiency, revealing a widely applicable selective advantage. Furthermore, we show that the distribution of cell lengths and curvatures observed across bacteria in nature is predicted by evolutionary trade-offs between three tasks influenced by shape: efficient swimming, the ability to detect chemical gradients, and reduced cost of cell construction. We therefore reveal shape as an important component of microbial fitness.