Yiping Ji, Mahalakshmi Sabanayagam, Peyman Moghadam, Hemanth Saratchandran, Simon Lucey
Large-scale transformer training and deployment are increasingly constrained by the transfer of activations, gradients, and optimizer states across accelerators. Low-bit quantization offers a natural remedy, but transformer activations are often heavy-tailed and outlier-dominated, making simple quantization highly lossy. We show that this difficulty is not only a property of the quantizer, but also of the architecture. Specifically, residual connections can drive transformer activations away from Gaussianity during training. Using controlled comparisons between residual and residual-free transformers, we demonstrate that this effect leads to substantially higher quantization error and accuracy degradation at low precision in residual models. We explain the phenomenon through an excess kurtosis analysis, showing that residual mixing can amplify non-Gaussianity, whereas dense mixing in residual-free models contracts non-Gaussianity. We then show that residual-free transformers can be made trainable using orthogonal initialization, spectral or second-order optimization, and depth-aware scaling of attention temperature. In language tasks, while there is a small drop in full precision performance, these models retain near-Gaussian activations and exhibit significantly improved robustness to low-bit quantization. Our results identify an accuracy--compressibility trade-off in transformer design and motivate architecture-level approaches to quantization-friendly foundation models.
Damien Teney, Liangze Jiang, Zachary Shinnick, Hemanth Saratchandran, Simon Lucey
Language models are typically trained with a single choice of architecture on diverse domains and data sources. Modern transformers have been extensively refined for such general-purpose learning, but are they equally effective across different subsets of the pretraining data? We investigate this question by training small language models from scratch on representative subsets of pretraining data such as web text, code, and mathematics. We introduce variants of transformers in which standard activation functions are replaced with learned splines tuned on specific datasets, providing a simple way to modify their inductive biases. Using a mix-and-match of architectures and datasets, we evaluate cross-domain transfer, i.e. how well does an architecture tuned for one domain perform on data from another? We find that the tuned transformer variants improve training efficiency or generalization on all seven of our tested datasets, but the gains are often domain-specific. For example, architectures tuned on a natural language dataset such as FineWeb perform well on TinyStories, whereas those tuned on mathematics perform poorly on natural language. We identify several mechanisms underlying these improvements, including wider loss basins and more abundant "lottery tickets". Our results show that different subsets of pretraining data can benefit from different learning mechanisms, highlighting a limitation of the prevailing trend towards a small set of general-purpose architectures and optimizers. This points to an opportunity to improve data efficiency by developing domain-specific learning strategies that retain the ability to train general-purpose models.