Efficient algorithms find optimal monotone transforms for calibration under strictly convex losses.
problem Calibrating estimations to improve performance with monotone transforms.
method Proposed linear-time and space algorithm for finding optimal monotone transforms for specific loss functions. Also proposed an anytime algorithm with linear space and pseudo-linearithmic time complexity.
result Optimal monotone transforms are unique and can be found efficiently for various strictly convex loss functions.
Transformers can learn optimal regression mixtures efficiently.
problem Limited adoption of tailored regression methods due to their model-specific nature.
method Constructed a generative process for a mixture of linear regressions and used transformers to learn optimal predictors.
result Transformers achieve low mean-squared error and make predictions close to the optimal procedure.
Researchers improve transformer networks' optimization and understanding.
problem Improving the understanding and optimization of transformer networks.
method Introducing a convex alternative to the self-attention mechanism and reformulating the training problem as a convex optimization problem.
result Revealed an implicit regularization mechanism that promotes sparsity across tokens.
Study on SignGD optimization of two-layer transformer on noisy data.
problem Understanding how SignGD optimizes transformers and its generalization.
method Analysis of a two-layer transformer with SignGD on a linearly separable noisy dataset.
result SignGD converges fast but has poor generalization on noisy data.
A new transformer model accelerates training with optimization techniques.
problem Training deep neural networks efficiently and effectively.
method Interprets transformer layers as optimization steps, applying Nesterov acceleration.
result The new model outperforms existing models on benchmark datasets.
Transformers can approximate Newton's method for logistic regression.
problem Implementing higher order optimization methods in Transformers.
method Linear attention Transformers with ReLU layers approximating second order optimization algorithms.
result Transformers can implement a single step of Newton's iteration for matrix inversion.
Transformers struggle to learn Markovian dynamics, showing NP-hard optimization challenges.
problem Understanding transformers' limitations in learning Markovian dynamical functions.
method Investigated through a structured ICL setup, analyzing loss landscapes and parameter optimization.
result Recovering optimal transformer parameters for Markovian functions is NP-hard.
Transformers achieve near-optimal dynamic regret in non-stationary reinforcement learning.
problem Understanding and handling non-stationary environments in reinforcement learning.
method Demonstrated that transformers can achieve nearly optimal dynamic regret bounds in non-stationary settings.
result Transformers can approximate and learn strategies for non-stationary environments, matching or outperforming existing expert algorithms.
FineMorphs models smooth transformations for multivariate regression.
problem Efficiently modeling complex transformations for multivariate regression.
method Optimal control of affine and diffeomorphic transformations using smooth vector fields.
result FineMorphs can reduce dimensionality and adapt to large datasets.
Transformer models align words through attention weights, closely approximating Optimal Transport.
problem Understanding the internal mechanism of transformer models in language processing.
method Empirical evidence and theoretical analysis of attention weights and their relation to Optimal Transport.
result Transformer models can simulate gradient descent on the dual of entropy-regularized OT problem, providing a theoretical foundation for token alignment.
Pion optimizes LLMs by preserving weight matrix singular values.
problem Training large language models (LLMs) with standard optimizers leads to unstable weight matrices.
method Pion uses orthogonal transformations to update weight matrices, preserving their singular values.
result Pion offers a stable alternative to standard optimizers for LLM pretraining and finetuning.
Optimizing data movement significantly improves transformer training efficiency.
problem Data movement is a major bottleneck in training transformers.
method Developed a recipe to globally optimize data movement in transformers.
result Achieved up to 1.30x performance improvement over state-of-the-art frameworks.
Transformers learn a mesa-optimizer to implement in-context learning.
problem Understanding the convergence of autoregressive training to a mesa-optimizer.
method Investigated a one-layer linear causal self-attention model autoregressively trained by gradient flow.
result Proved that autoregressive training converges to a gradient descent step for an OLS problem, validating the mesa-optimizer hypothesis.
Kernel estimator optimally recovers function from noisy exponential Radon transform.
problem Inverting noisy exponential Radon transform of a function.
method Proposed a kernel estimator to estimate the true function.
result The estimator converges to the true function at minimax optimal rate.
In many state-of-the-art compression systems, signal transformation is an integral part of the encoding and decoding process, where transforms provide compact representations for the signals of interest. This paper introduces a class of transforms called graph-based transforms (GBTs) for video compression, and proposes…
Fusion of transformer networks using optimal transport for improved performance.
problem Improving performance of transformer-based models through fusion.
method Exploiting optimal transport for soft alignment of transformer components.
result Consistently outperforms vanilla fusion and individual parent models.
Transformers use a unique Hessian structure that differs from classical networks, affecting optimization.
problem Understanding the unique optimization landscape of Transformers.
method Theoretical Hessian analysis of a single self-attention layer in Transformers.
result Transformers have a highly non-linear Hessian structure, distinguishing them from classical networks.
Standard Transformers approximate Hölder functions and achieve optimal nonparametric regression rate.
problem Approximating Hölder functions and achieving optimal nonparametric regression rate with Transformers.
method Using the size tuple and dimension vector metrics, the paper characterizes Transformer structures and derives upper bounds for their Lipschitz constant and memorization capacity.
result Standard Transformers achieve the minimax optimal rate in nonparametric regression for Hölder target functions.
Solves optimal stopping for Gauss-Markov bridges using time-space transformation.
problem Optimal stopping problem of a Gauss-Markov bridge.
method Time-space transformation approach, Picard iteration algorithm.
result Lipschitz continuity of the optimal stopping boundary and its characterization.
Transformers can efficiently approximate nonparametric regression with minimal parameters and sequences.
problem Efficiently approximating nonparametric regression functions with transformers.
method Kernel-weighted polynomial basis and gradient descent.
result Achieves minimax optimal rate of convergence with fewer parameters and sequences.
Transforms robust algorithms into private ones with optimal error rates.
problem Balancing privacy and robustness in machine learning.
method Black-box transformation method to convert robust algorithms to private ones with optimal error rates.
result Optimal private estimators for various tasks, including Gaussian and PCA.
Transforms game optimization dynamics into frequency domain for precise hyperparameter analysis.
problem Analyzing convergence of hyperparameters in game optimization.
method Frequency-domain framework using High-Resolution Differential Equations (HRDEs) and Laplace transforms.
result Derives precise convergence criteria for the Lookahead algorithm.
Transformers can learn optimal variable selection in group-sparse classification.
problem Understanding how transformers leverage attention to select relevant variables in group-sparse classification.
method Training a one-layer transformer using gradient descent to select variables from one group of input variables.
result A one-layer transformer can correctly leverage the attention mechanism to select variables, disregarding irrelevant ones.
Continuum transformers learn operators in context via gradient descent.
problem Generalizing transformers to handle infinite-dimensional inputs for in-context learning.
method Gradient descent in an operator RKHS, leveraging generalized representer theorems and gradient flows.
result Operator learned in context is Bayes Optimal Predictor in infinite depth limit.
Transformers converge linearly to optimal models for Gaussian mixtures classification.
problem Theoretical understanding of transformers' in-context classification.
method Gradient descent training of a single-layer transformer for Gaussian mixtures classification.
result Transformers converge linearly to globally optimal models for Gaussian mixtures classification.
Enhanced Transformer models predict ETF portfolio performance by optimizing covariance and semi-covariance matrices.
problem Static covariance estimates fail to capture dynamic market fluctuations and non-linear correlations.
method Transformer-based models for real-time covariance and semi-covariance predictions.
result Portfolios optimized with semi-covariance matrix outperform those with standard covariance matrix, especially in volatile conditions.
PPT optimizes transformer behavior by steering its latent posterior using prior samples.
problem Eliciting desired behavior from transformers without backpropagation.
method Posterior Prefix Tuning (PPT) uses predictive Monte Carlo (PMC) samples and importance sampling to optimize the latent posterior.
result PPT optimizes transformer behavior without backpropagation, achieving high utility across different utility functions.
New insights into how data transformations affect self-supervised clustering.
problem Impact of data transformations on self-supervised clustering convergence.
method Theoretical and empirical analysis of various data transformations.
result Certain transformations help in faster convergence of self-supervised clustering.
This work introduces a transformation-based learner model for classification forests. The weak learner at each split node plays a crucial role in a classification tree. We propose to optimize the splitting objective by learning a linear transformation on subspaces using nuclear norm as the optimization criteria. The le…
Transformers can handle endogeneity in linear regression using IV methods.
problem Endogeneity in in-context linear regression models.
method Transformer architecture with gradient-based bi-level optimization and in-context pretraining.
result Transformers provide more robust predictions and estimates than 2SLS in endogenous scenarios.
Sparse transformer architecture improves accuracy and speed in generative modeling and inverse problems.
problem Improving accuracy and speed in generative modeling and inverse problems.
method Proposes a sparse transformer architecture using regularized Wasserstein proximal operator with L 1 L_1 L 1 prior. result Sparse transformer achieves higher accuracy and faster convergence than classical methods.
This paper considers fair probabilistic binary classification where the outputs of primary interest are predicted probabilities, commonly referred to as scores. We formulate the problem of transforming scores to satisfy fairness constraints that are linear in conditional means of scores while minimizing a cross-entropy…
Recurrent neural network (RNN)'s architecture is a key factor influencing its performance. We propose algorithms to optimize hidden sizes under running time constraint. We convert the discrete optimization into a subset selection problem. By novel transformations, the objective function becomes submodular and constrain…
A new model improves CT image quality from low-dose scans.
problem Improving CT image quality from low-dose scans.
method Multi-layer Residual Sparsifying Transform (MRST) learning model for low-dose CT reconstruction.
result The MRST model outperforms conventional methods in maintaining subtle details.
We prove that the global minimum of the backpropagation (BP) training problem of neural networks with an arbitrary nonlinear activation is given by the ridgelet transform. A series of computational experiments show that there exists an interesting similarity between the scatter plot of hidden parameters in a shallow ne…
Efficiently optimizes CNN and RNN parameters on Stiefel manifold.
problem Computational expense in optimizing orthonormal matrices on Stiefel manifold.
method Cayley transform for efficient retraction and vector transport on Stiefel manifold.
result Cayley SGD and ADAM achieve faster convergence and less training time.
Improved hyperparameter optimization using simplified Transformer blocks.
problem Discovering optimal architectures in high-dimensional search spaces with limited exploration budgets.
method Simplified Transformer block for modeling hyper-parameter dependencies, actor-critic style algorithm, ensembling.
result Outperformed most algorithms on NAS-Bench-101 and Random Search in discovering more accurate model architectures.
Algorithm finds optimal affine transformation to minimize overall distortion.
problem Minimizing distortion in affine transformations.
method Riemannian geometry approach to define and minimize distortion.
result Mean distorting transformation found for minimizing overall distortion.
Derives an empirical capacity model for self-attention neural networks.
problem Theoretical capacity of large transformer models is not fully utilized by current optimization algorithms.
method Analyzes memory capacity of transformers using synthetic training data and common training algorithms.
result Derives an empirical capacity model (ECM) for a generic transformer.
Transforms offline greedy algorithms to online algorithms for combinatorial problems.
problem Online decision-making in time-varying combinatorial environments.
method General framework using Blackwell approachability and Bandit Blackwell approachability.
result Achieves O ( T ) O(\sqrt{T}) O ( T ) regret in full information setting and O ( T 2 / 3 ) O(T^{2/3}) O ( T 2/3 ) regret in bandit setting. Transformer RL optimizes A/B testing for time series experiments.
problem Challenges in applying A/B testing to time series experiments, especially with limited history and strong assumptions.
method Transformer reinforcement learning approach that conditions allocation on full history and optimizes MSE without restrictive assumptions.
result Consistently outperforms existing designs in synthetic, simulator, and real-world data.
Transformers learn new tasks from few examples via optimal approximation.
problem Learning new tasks from limited examples using large language models.
method Developed approximation and generalization error bounds for transformers trained on nonparametric regression tasks.
result Transformers achieve minimax optimal estimation risk in context.
Transformers reduce redundancy by focusing on invariant relational quantities.
problem Substantial internal redundancy in Transformer models due to coordinate-dependent representations and continuous symmetries.
method Reformulate representations, attention mechanisms, and optimization dynamics in terms of invariant relational quantities, eliminating redundant degrees of freedom by construction.
result Architectures that operate directly on relational structures, providing a principled geometric framework for reducing parameter redundancy and analyzing optimization.
Many problems in machine learning involve calculating correspondences between sets of objects, such as point clouds or images. Discrete optimal transport provides a natural and successful approach to such tasks whenever the two sets of objects can be represented in the same space, or at least distances between them can…
Transforms ensemble predictions to maintain interpretability.
problem Loss of interpretability in deep ensembles.
method Proposes transformation ensembles that aggregate predictions while preserving interpretability.
result Transformation ensembles yield better predictions than individual models and maintain interpretability.
OptFormer learns universal HPO from diverse datasets.
problem Learning HPO from experiments with different hyperparameters.
method Text-based Transformer framework for joint policy and function prediction.
result OptFormer can imitate multiple HPO algorithms and improve predictions.
Proposes a differentiable STFT for more efficient optimization of hop length.
problem Efficient optimization of hop length in STFT for better temporal control.
method Introduces a differentiable version of STFT with continuous hop length.
result Improves optimization methods like gradient descent for STFT.
The paper solves a complex financial optimization problem using a novel mathematical technique.
problem Optimizing portfolio selection in financial markets.
method Maximal monotone operator method and Riccati transformation.
result Existence and uniqueness of a solution to the transformed parabolic equation in a Sobolev space.