compute-optimal training
Latest papers
8 papers0 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.
Classical neural scaling laws model excess risk as a separable power law in model capacity and dataset size . At finite budgets, however, empirical learning curves and compute-optimal allocations depart from this log-linear frontier. This paper analyzes how spectral and domain heterogeneity govern these finite-scale departures. Along the capacity axis, Mellin--Barnes analysis of covariance resolvents yields a three-term expansion where competing spectral and regularization modes produce finite-scale curvature and logarithmic transitions. Because fitting multiple power laws on narrow pilot grids is ill-conditioned, we eliminate the loss floor via first-order Aitken differencing to obtain a well-conditioned closed-form initializer. Along the data axis, KKT duality reduces -domain mixing to scalar water-filling, yielding finite-budget bottleneck bounds, an online sampling curriculum, and a simplex Hessian metric for cross-domain transfer. Along the iso-compute frontier , we prove that the optimal allocation exponent drifts in proportion to capacity and data exponent variances, while Schur-complement reduction separates intrinsic drift from frozen-hyperparameter bias. Across 45 operator spectra, Pythia (70M--12B), Chinchilla (245 runs), and RegMix (17 domains), our estimators achieve holdout MAPE, cut high-compute allocation regret by up to , and reduce cross-scale mixture RMSE by with zero selection regret.
Training and Scaling Compute-Optimal Physiological Waveform Foundation Models
We investigate the scaling laws and compute-optimal training of physiological waveform foundation models (FMs). We train Aether, a family of over one hundred FMs ranging from 20M to 2.1B parameters, on up to 36.3M hours of physiological waveforms. We construct eight clinical prediction tasks from MIMIC-III and evaluate the FMs through linear probing. The 720M FM outperforms all existing baseline FMs across all eight tasks. A scaling law of model size, pretraining hours, and labeled patients predicts downstream ranking error, i.e. , effectively with prediction MAE at held-out resource scales and MAE when extrapolating to 2.1B parameters. We present three findings: (1) Compute-optimal training scales both FM size and pretraining hours. Under the fitted law, a increase in compute FLOPs scales model size by and pretraining hours by . (2) Larger FMs use waveform data more efficiently, and greater pretraining exposure increases the benefit of model scaling. Starting from 25M parameters and 4.8M pretraining hours, doubling FM size reduces the predicted hours needed for the same performance by . (3) Pretraining and clinical supervision reinforce each other: more labeled patients increase the return to pretraining, while larger FMs and longer pretraining reduce labeling requirements. For the example of the 720M FM, extending pretraining from 120K to 36.3M hours reduces the predicted patient requirement by at a target ranking error. These findings provide a quantitative training recipe and a promising and durable scaling path for physiological waveform modeling and downstream clinical prediction.
How Model Growth, Recursion, and Boundary Operators Influence Scaling Exponents
Scaling laws predict how loss decreases with increases in computation. We show, contrary to conventional wisdom, that architectural interventions can modify scaling exponents in pre-training, leading to power-law improvements in performance as computation increases. As an anchoring point, we consider the architectural formulation of looped transformers. Although not typically used in this way, looping, also known as recursive depth, provides a mechanism for model growth, by increasing the number of loops during training. Model growth, with and without shared weights, provides the biggest changes to the scaling exponents. In particular, a 7.4B model growth architecture matches GPT-3 13B on CORE with roughly less compute, and has compute efficiency gains that increase with scale. Moreover, simply using a boundary operator in a vanilla transformer, which normalizes and injects an earlier block, also provides an exponent increase, although to a lesser extent. In the data-constrained, multi-epoch setting, standard looping has a useful regularizing effect, where we find it is compute-optimal to increase the number of loops with scale. These results can be understood through the lens of computational depth: for a given computational budget, we wish to increase the usable depth of the transformer, which can lead to efficiency gains that increase with scale.
Unifying Data, Memory, and Compute Efficiency in LLM training: A Survey
Resource constraints increasingly determine what can be trained, fine-tuned, and deployed in large language models (LLMs), yet efficiency is often studied through isolated techniques rather than as an interacting system of limits. This survey adopts a constraint-centric perspective and organizes recent progress around three coupled bottlenecks: data efficiency (what to train on), memory efficiency (how to fit training), and compute budget awareness (when and where to spend FLOPs). On the data axis, we review selection and pruning methods that maximize learning per token, ranging from scalable proxy signals based on learning dynamics to gradient- and influence-based scoring, as well as difficulty-aware and curriculum-style strategies. We highlight emerging evidence that different notions of good data dominate in different regimes, implying that optimal subsets depend on the task objective and resource budget rather than being universal. On the systems side, we show that GPU memory, not raw compute, is often the dominant bottleneck in fine-tuning, and that effective scaling requires jointly reducing weight storage, optimizer states, and activation memory rather than optimizing any single component in isolation. Beyond memory, we frame training and inference as compute-governed processes in which optimization, data selection, and decoding must explicitly account for finite FLOP budgets. We review evidence for compute-optimal allocation and stopping rules, where computation should be halted or reallocated once marginal performance gains fall below a budget-dependent threshold. Together, these results unify compute-aware data selection, scaling laws, and adaptive inference under a common principle of resource-conditioned decision-making.
Scaling Laws for Behavioral Foundation Models over User Event Sequences
Foundation models are increasingly trained on sequences of user actions in recommendation, payments, fraud, and commerce, but these models still lack the kind of compute calibration that scaling laws provide for language models. We study a common two-part behavioral-model architecture: a feature-based event embedder maps each multi-modal item to a vector, and a decoder-only transformer predicts the next event from the resulting sequence. Across roughly 600 runs on real interaction data, spanning - training FLOPs, we jointly vary four deployment-relevant axes: the two-part parameter split, critical batch size, model/data allocation, and the number of sampled negatives used after freezing the embedder. A small embedder ( of parameters) is compute-optimal at every budget we test because embedder parameters are both more expensive per step and exposed to far more repeated items than contextualizer parameters. Compute-optimal training is data-heavy relative to text at low compute, but its ratio moves toward the Chinchilla heuristic as compute increases. The sampled training objective and deployed ranking metrics disagree in ways that themselves scale: critical batch size, optimal negative count after freezing, and the agreement between loss and ranking quality all shift with compute and with the chosen evaluation metric. For negative sampling, larger budgets increasingly prefer more negatives; by FLOPs the active constraint is candidate-axis memory rather than FLOPs. In behavioral foundation models, the evaluation metric is therefore part of the scaling law: changing it can change the compute-optimal recipe.
Practical Scaling Laws: Converting Compute into Performance in a Data-Constrained World
The scaling laws guiding modern model training were calibrated for a single regime: data-rich, single-epoch pretraining. The dominant such scaling law form, Chinchilla's , has three structural limitations outside that regime: it diverges as unique data shrinks instead of saturating at the uninformed baseline; it cannot represent overfitting when capacity exceeds the data; and it conflates total examples seen with unique examples available. We propose a closed-form extension, with , that decomposes loss into undercapacity, undertraining, and overfitting terms. It saturates between the irreducible loss and an uninformed baseline fixed by the loss type, and reduces to Chinchilla in the data-rich, single-epoch limit. We validate it on four multi-epoch experiments spanning four architecture families (MLPs, ResNets, Fourier neural operators, and transformers) across vision, scientific ML, and language domains, and refit it to five published LLM scaling-law grids. Extrapolating to higher compute and larger unique data than seen at fit time, our form achieves state-of-the-art RMSE on every published LLM grid we evaluate and on most cells of our constructed experiments. Once calibrated, the form admits a cost-aware allocation that recovers Chinchilla's optimum when data is free and shifts toward smaller corpora and more epochs as data grows expensive.
On Neural Scaling Laws for Weather Emulation through Continual Training
Neural scaling laws, which in some domains can predict the performance of large neural networks as a function of model, data, and compute scale, are the cornerstone of building foundation models in Natural Language Processing and Computer Vision. We study neural scaling in Scientific Machine Learning, focusing on models for weather forecasting. To analyze scaling behavior in as simple a setting as possible, we adopt a minimal, scalable, general-purpose Swin Transformer architecture, and we use continual training with constant learning rates and periodic cooldowns as an efficient training strategy. We show that models trained in this minimalist way follow predictable scaling trends and can outperform standard cosine learning rate schedules. Cooldown phases can be repurposed to improve downstream performance, e.g., enabling accurate multi-step rollouts over longer forecast horizons or sharper predictions through spectral loss adjustments. We also systematically explore a wide range of model and dataset sizes under various compute budgets to construct IsoFLOP curves, and we identify compute-optimal training regimes. Extrapolating these trends to larger scales highlights potential performance limits, demonstrating that neural scaling can serve as an important diagnostic for efficient resource allocation. We open-source our code for reproducibility
Problems with Chinchilla Approach 2: Systematic Biases in IsoFLOP Parabola Fits
Chinchilla Approach 2 is among the most widely used methods for fitting neural scaling laws. Its parabolic approximation introduces systematic biases in compute-optimal allocation estimates, even on noise-free synthetic data. Applied to published Llama 3 IsoFLOP data at open frontier compute scales, these biases imply a parameter underallocation corresponding to 6.5% of the FLOP training budget and $1.4M (90% CI: $412K-$2.9M) in unnecessary compute at 50% H100 MFU. Simulated multimodal model misallocations show even greater opportunity costs due to higher loss surface asymmetry. Three sources of this error are examined: IsoFLOP sampling grid width (Taylor approximation accuracy), uncentered IsoFLOP sampling, and loss surface asymmetry (). Chinchilla Approach 3 largely eliminates these biases but is often regarded as less data-efficient, numerically unstable, prone to local minima, and harder to implement. Each concern is shown to be unfounded or addressable, especially when the partially linear structure of the objective is exploited via Variable Projection, enabling unbiased inference on all five loss surface parameters through a two-dimensional optimization that is well-conditioned, analytically differentiable, and amenable to dense, or even exhaustive, grid search. It may serve as a more convenient replacement for Approach 2 or a more scalable alternative for adaptations of Approach 3 to richer scaling law formulations. See https://github.com/Open-Athena/vpnls for details and https://openathena.ai/scaling-law-analysis for other results from this study.