Searcharxiv⌕ Search

arXiv subjects

Kristin Branson

Publications and source records attributed to Kristin Branson.

17 recordsLinked to original sources

AgentSSL: Can MLE Agents Leverage Unlabeled Data?

Applying machine learning systems to new domains introduces bottlenecks in both labeled data acquisition and manual pipeline engineering. While recent MLE agents show promise in automating pipeline design, they have been studied almost exclusively in fully supervised settings, leaving them untested in realistic regimes where labeled data is scarce but unlabeled data is abundant. In this work, we introduce Agentic Semi-Supervised Learning (AgentSSL), framing SSL as a program search problem and studying how agents navigate this space under limited supervision. We find that even under weak feedback and matched compute, agents can synthesize code that combines and adapts established SSL techniques, exceeding the strongest human-engineered baselines in 8 of 12 settings by up to +21.8%. However, our results identify program selection as a critical bottleneck in AgentSSL, where performance drops by as much as 47% when selecting based on the agent's feedback metric. To systematically study this bottleneck, we introduce ProgramSelectBench, a large-scale benchmark with a combined total of 16,977 agent-generated and human-engineered SSL programs, and evaluate both unsupervised and active program selection methods. We further evaluate AgentSSL on real-world ecology detection tasks, highlighting the opportunities and challenges of transferring agent-discovered strategies beyond controlled benchmarks.

cs.AI↗

Neurodata Without Boredom: Benchmarking Agentic AI for Data Reuse

Neuroscience data are fragmented across labs, experimental paradigms, and storage formats, and data reuse often requires substantial manual effort. Standardized formats have been proposed in response, but a fundamental tension persists: formats flexible enough for diverse experiments are rarely self-explanatory, while fully descriptive datasets demand documentation and curation effort that few labs can sustain. Coding agents, which can read code and text quickly with apparent attention to details humans tend to skim, are a natural candidate to reduce this burden. To measure how well coding agents perform data reuse, we benchmark them on eight recent papers with large-scale mouse neural recordings spanning diverse recording modalities, behavioral paradigms, and formats. Given the data, code, and paper, the agents must reformat the data for a common downstream task: training a decoder from neural activity to task and behavioral variables. Evaluating the resulting solutions, however, is challenging, since many conversion decisions are under-specified and several choices are defensible. Yet a subtle but scientifically significant error can invalidate the dataset in ways aggregate metrics can miss. We therefore pair outcome-based metrics with a process-based rubric, scored by two human evaluators against manual reference solutions. We find that agents succeed on most subtasks but rarely produce a fully error-free end-to-end solution; we characterize their mistakes and suggest data-sharing practices for agent-assisted reuse. Finally, we find that agent judges are unreliable at catching errors on their own, but can automate process-based evaluation when given reference solutions.

cs.LG↗

Modeling Fly Social Behavior with Agent-Centric Pose Forecasting

Understanding animal behavior at an algorithmic level -- what animals attend to, how they form internal representations, and how this maps to action -- remains a central challenge in neuroethology. We explore how well large generative models capture properties of fly social behavior. We combine transformers with agent-centric representations. Models input egocentric sensory observations and output egocentric movements, mirroring biological constraints. Social behavior emerges from agents independently sensing and responding to one another. We demonstrate that this simple model captures many properties of fly behavior, outperforming the world-centric representation and achieving SOTA on MABe 2022-fly. We systematically evaluate properties of the representation important for capturing the behavior distribution through a series of lesioning experiments. These comparisons were enabled by a new, general-purpose library for animal-centric pose forecasting.

cs.LG↗

WildFin: An In-the-Wild Dataset for Fish Behavioral Recognition

Recent advances in field technology have led to a massive influx of in-the-wild video data for ecological science. The primary bottleneck in leveraging this data is the high cost of expert annotation. While computer vision offers a potential solution, current models frequently fail when deployed in complex marine environments. To characterize these failures, we introduce WildFin, a novel benchmark for fish behavior recognition collected and annotated by ecologists. WildFin spans two critical real-world paradigms: stationary cameras monitoring groups of fish and dynamic divers following individual subjects. The dataset represents a massive curation effort, involving 1,350 hours of fieldwork and 600 hours of expert annotation to produce 9 hours of behavioral data with over 2 million frame-by-frame labels. We benchmark modern vision foundation models and quantify tradeoffs between static and spatiotemporal architectures, revealing the substantial gap that remains between current model capabilities and the demands of real-world underwater behavioral analysis. Project website: https://team-wildfin.github.io/.

cs.CV↗

A case study of evaluating AI agents on a neuroscience data-to-discovery pipeline

Agentic AI offers a promising path to automating software development bottlenecks in scientific research pipelines, particularly for stages that take domain experts days to months to build and where correctness and robustness matter more than implementation details. We present an empirical study of general-purpose coding agents on a fly optogenetics data-to-discovery pipeline. We assess agents on tasks and datasets substantially larger than existing benchmarks and evaluation criteria grounded in domain expert standards. We show that agents can solve several pipeline stages, suggesting stage-level automation is tractable. By analyzing agents' code iterations, we show they struggle most without a pre-defined criterion, when they must instead use their scientific judgment to assess their current solution. Mirroring scientists, they sometimes attempt visual inspection of intermediate outputs for self-evaluation, but largely fail to interpret what they see or act on it appropriately. Solving the end-to-end pipeline requires stringing together successes across all stages, which is beyond agents' current abilities. We identify challenges largely absent from existing benchmarks, including computational resource management and generalization to held-out data. Finally, we distill principles for constructing scientific tasks and rigorous evaluation criteria for open-ended problems.

cs.AI↗

MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of Behavior

We introduce MABe22, a large-scale, multi-agent video and trajectory benchmark to assess the quality of learned behavior representations. This dataset is collected from a variety of biology experiments, and includes triplets of interacting mice (4.7 million frames video+pose tracking data, 10 million frames pose only), symbiotic beetle-ant interactions (10 million frames video data), and groups of interacting flies (4.4 million frames of pose tracking data). Accompanying these data, we introduce a panel of real-life downstream analysis tasks to assess the quality of learned representations by evaluating how well they preserve information about the experimental conditions (e.g. strain, time of day, optogenetic stimulation) and animal behavior. We test multiple state-of-the-art self-supervised video and trajectory representation learning methods to demonstrate the use of our benchmark, revealing that methods developed using human action datasets do not fully translate to animal datasets. We hope that our benchmark and dataset encourage a broader exploration of behavior representation learning methods across species and settings.

cs.LG↗

Evaluation metrics for behaviour modeling

A primary difficulty with unsupervised discovery of structure in large data sets is a lack of quantitative evaluation criteria. In this work, we propose and investigate several metrics for evaluating and comparing generative models of behavior learned using imitation learning. Compared to the commonly-used model log-likelihood, these criteria look at longer temporal relationships in behavior, are relevant if behavior has some properties that are inherently unpredictable, and highlight biases in the overall distribution of behaviors produced by the model. Pointwise metrics compare real to model-predicted trajectories given true past information. Distribution metrics compare statistics of the model simulating behavior in open loop, and are inspired by how experimental biologists evaluate the effects of manipulations on animal behavior. We show that the proposed metrics correspond with biologists' intuitions about behavior, and allow us to evaluate models, understand their biases, and enable us to propose new research directions.

cs.LG↗

Detecting the Starting Frame of Actions in Video

In this work, we address the problem of precisely localizing key frames of an action, for example, the precise time that a pitcher releases a baseball, or the precise time that a crowd begins to applaud. Key frame localization is a largely overlooked and important action-recognition problem, for example in the field of neuroscience, in which we would like to understand the neural activity that produces the start of a bout of an action. To address this problem, we introduce a novel structured loss function that properly weights the types of errors that matter in such applications: it more heavily penalizes extra and missed action start detections over small misalignments. Our structured loss is based on the best matching between predicted and labeled action starts. We train recurrent neural networks (RNNs) to minimize differentiable approximations of this loss. To evaluate these methods, we introduce the Mouse Reach Dataset, a large, annotated video dataset of mice performing a sequence of actions. The dataset was collected and labeled by experts for the purpose of neuroscience research. On this dataset, we demonstrate that our method outperforms related approaches and baseline methods using an unstructured loss.

cs.CV↗

Are skip connections necessary for biologically plausible learning rules?

Backpropagation is the workhorse of deep learning, however, several other biologically-motivated learning rules have been introduced, such as random feedback alignment and difference target propagation. None of these methods have produced a competitive performance against backpropagation. In this paper, we show that biologically-motivated learning rules with skip connections between intermediate layers can perform as well as backpropagation on the MNIST dataset and are robust to various sets of hyper-parameters.

cs.NE↗

Importance Weighted Adversarial Variational Autoencoders for Spike Inference from Calcium Imaging Data

The Importance Weighted Auto Encoder (IWAE) objective has been shown to improve the training of generative models over the standard Variational Auto Encoder (VAE) objective. Here, we derive importance weighted extensions to AVB and AAE. These latent variable models use implicitly defined inference networks whose approximate posterior density q_ϕ(z|x) cannot be directly evaluated, an essential ingredient for importance weighting. We show improved training and inference in latent variable models with our adversarially trained importance weighting method, and derive new theoretical connections between adversarial generative model training criteria and marginal likelihood based methods. We apply these methods to the important problem of inferring spiking neural activity from calcium imaging data, a challenging posterior inference problem in neuroscience, and show that posterior samples from the adversarial methods outperform factorized posteriors used in VAEs.

cs.LG↗

Stochastic Neighbor Embedding under f-divergences

The t-distributed Stochastic Neighbor Embedding (t-SNE) is a powerful and popular method for visualizing high-dimensional data. It minimizes the Kullback-Leibler (KL) divergence between the original and embedded data distributions. In this work, we propose extending this method to other f-divergences. We analytically and empirically evaluate the types of latent structure-manifold, cluster, and hierarchical-that are well-captured using both the original KL-divergence as well as the proposed f-divergence generalization, and find that different divergences perform better for different types of structure. A common concern with $t$-SNE criterion is that it is optimized using gradient descent, and can become stuck in poor local minima. We propose optimizing the f-divergence based loss criteria by minimizing a variational bound. This typically performs better than optimizing the primal form, and our experiments show that it can improve upon the embedding results obtained from the original $t$-SNE criterion as well.

cs.LG↗

Quantitatively Evaluating GANs With Divergences Proposed for Training

Generative adversarial networks (GANs) have been extremely effective in approximating complex distributions of high-dimensional, input data samples, and substantial progress has been made in understanding and improving GAN performance in terms of both theory and application. However, we currently lack quantitative methods for model assessment. Because of this, while many GAN variants are being proposed, we have relatively little understanding of their relative abilities. In this paper, we evaluate the performance of various types of GANs using divergence and distance functions typically used only for training. We observe consistency across the various proposed metrics and, interestingly, the test-time metrics do not favour networks that use the same training-time criterion. We also compare the proposed metrics to human perceptual scores.

cs.LG↗

An empirical analysis of the optimization of deep network loss surfaces

The success of deep neural networks hinges on our ability to accurately and efficiently optimize high-dimensional, non-convex functions. In this paper, we empirically investigate the loss functions of state-of-the-art networks, and how commonly-used stochastic gradient descent variants optimize these loss functions. To do this, we visualize the loss function by projecting them down to low-dimensional spaces chosen based on the convergence points of different optimization algorithms. Our observations suggest that optimization algorithms encounter and choose different descent directions at many saddle points to find different final weights. Based on consistency we observe across re-runs of the same stochastic optimization algorithm, we hypothesize that each optimization algorithm makes characteristic choices at these saddle points.

cs.LG↗

Network-size independent covering number bounds for deep networks

We give a covering number bound for deep learning networks that is independent of the size of the network. The key for the simple analysis is that for linear classifiers, rotating the data doesn't affect the covering number. Thus, we can ignore the rotation part of each layer's linear transformation, and get the covering number bound by concentrating on the scaling part.

cs.LG↗

Learning recurrent representations for hierarchical behavior modeling

We propose a framework for detecting action patterns from motion sequences and modeling the sensory-motor relationship of animals, using a generative recurrent neural network. The network has a discriminative part (classifying actions) and a generative part (predicting motion), whose recurrent cells are laterally connected, allowing higher levels of the network to represent high level phenomena. We test our framework on two types of data, fruit fly behavior and online handwriting. Our results show that 1) taking advantage of unlabeled sequences, by predicting future motion, significantly improves action detection performance when training labels are scarce, 2) the network learns to represent high level phenomena such as writer identity and fly gender, without supervision, and 3) simulated motion trajectories, generated by treating motion prediction as input to the network, look realistic and may be used to qualitatively evaluate whether the model has learnt generative control rules.

cs.AI↗

Sample complexity of learning Mahalanobis distance metrics

Metric learning seeks a transformation of the feature space that enhances prediction quality for the given task at hand. In this work we provide PAC-style sample complexity rates for supervised metric learning. We give matching lower- and upper-bounds showing that the sample complexity scales with the representation dimension when no assumptions are made about the underlying data distribution. However, by leveraging the structure of the data distribution, we show that one can achieve rates that are fine-tuned to a specific notion of intrinsic complexity for a given dataset. Our analysis reveals that augmenting the metric learning optimization criterion with a simple norm-based regularization can help adapt to a dataset's intrinsic complexity, yielding better generalization. Experiments on benchmark datasets validate our analysis and show that regularizing the metric can help discern the signal even when the data contains high amounts of noise.

cs.LG↗

Multi-camera Realtime 3D Tracking of Multiple Flying Animals

Automated tracking of animal movement allows analyses that would not otherwise be possible by providing great quantities of data. The additional capability of tracking in realtime - with minimal latency - opens up the experimental possibility of manipulating sensory feedback, thus allowing detailed explorations of the neural basis for control of behavior. Here we describe a new system capable of tracking the position and body orientation of animals such as flies and birds. The system operates with less than 40 msec latency and can track multiple animals simultaneously. To achieve these results, a multi target tracking algorithm was developed based on the Extended Kalman Filter and the Nearest Neighbor Standard Filter data association algorithm. In one implementation, an eleven camera system is capable of tracking three flies simultaneously at 60 frames per second using a gigabit network of nine standard Intel Pentium 4 and Core 2 Duo computers. This manuscript presents the rationale and details of the algorithms employed and shows three implementations of the system. An experiment was performed using the tracking system to measure the effect of visual contrast on the flight speed of Drosophila melanogaster. At low contrasts, speed is more variable and faster on average than at high contrasts. Thus, the system is already a useful tool to study the neurobiology and behavior of freely flying animals. If combined with other techniques, such as `virtual reality'-type computer graphics or genetic manipulation, the tracking system would offer a powerful new way to investigate the biology of flying animals.

cs.CV↗