REVIEW 12 cited by
Measure-to-measure interpolation using Transformers
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Measure-to-measure interpolation using Transformers
read the original abstract
Transformers are deep neural network architectures that underpin the recent successes of large language models. Unlike more classical architectures that can be viewed as point-to-point maps, a Transformer acts as a measure-to-measure map implemented as specific interacting particle system on the unit sphere: the input is the empirical measure of tokens in a prompt and its evolution is governed by the continuity equation. In fact, Transformers are not limited to empirical measures and can in principle process any input measure. As the nature of data processed by Transformers is expanding rapidly, it is important to investigate their expressive power as maps from an arbitrary measure to another arbitrary measure. To that end, we provide an explicit choice of parameters that allows a single Transformer to match $N$ arbitrary input measures to $N$ arbitrary target measures, under the minimal assumption that every pair of input-target measures can be matched by some transport map.
Forward citations
Cited by 12 Pith papers
-
Reachability and asymptotics of Gaussian Transformer dynamics
Gaussian distributions are invariant under the mean-field Transformer flow, reducing infinite-dimensional dynamics to a bilinear control system on mean and covariance with explicit reachability and stability results.
-
Kinetic theory for Transformers and the lost-in-the-middle phenomenon
A mean-field kinetic theory derivation produces a closed-form U-shaped token retrieval profile that explains the lost-in-the-middle phenomenon in Transformers.
-
Transformer-like Inference from Optimal Control
Derives transformer-like dual-filter inference layers from first-principles optimal control on nonlinear discrete and linear Gaussian sequence models.
-
Stochastic Scaling Limits and Synchronization by Noise in Deep Transformer Models
Transformers converge pathwise to a stochastic particle system and SPDE in the scaling limit, exhibiting synchronization by noise and exponential energy dissipation when common noise is coercive relative to self-atten...
-
Continuous transformations of probability measures and their transport representations
Lipschitz continuous transformations F of probability measures w.r.t. Wasserstein distance admit continuous transport maps f(·,μ) such that F(μ) = f(·,μ)_# μ.
-
Constructive conditional normalizing flows
Explicit constructions approximate diffeomorphisms and pushforward measures via continuity equation flows with perceptron velocity fields of piecewise constant weights, using polar-like decompositions and probabilisti...
-
Perceptrons and localization of attention's mean-field landscape
In the mean-field limit of attention with perceptron blocks, critical points of the energy landscape are generically atomic and localized on subsets of the unit sphere.
-
Exact Sequence Interpolation with Transformers
Transformers with O(sum m^j) blocks and O(d sum m^j) parameters can exactly interpolate any finite dataset of input sequences in R^d to output sequences of lengths m^j.
-
Propagation of Chaos in Contextual Flow Maps
Derives forward and backward propagation-of-chaos bounds for finite vs. infinite-context transformers modeled as contextual flow maps, achieving Wasserstein rate n^{-1/d} generally and n^{-1/2} for transformer-like cases.
-
Multi-Headed Transformer Architectures as Time-dependent Wasserstein Gradient Flows
Models multi-head transformer data flow as time-dependent Wasserstein gradient flows of an attention-capturing interaction energy, with proofs on omega-limit stationary points and stability under weight and input pert...
-
Measure-to-measure Regression with Transformers
Formalizes nonlinear M2M regression and introduces transformer architectures as static maps and dynamic velocity fields between probability measures, tested on synthetic, particle, and organoid datasets.
-
Optimal and Diffusion Transports in Machine Learning
A survey showing how optimal transport, diffusion models, and transformer dynamics all fit into a common framework of time-evolving probability measures.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.