12 papers
Hilbert Operator for Progressive Encoding (HOPE): A Mathematical Framework for Deconstructing Learned Representations in Deep Networks
Hossein Mobahi, Peter L. Bartlett
Deep neural networks encode complex representations, but deconstructing this internal knowledge remains a challenge. Given the link between learning and compression, network compre…
Risk Comparisons in Linear Regression: Implicit Regularization Dominates Explicit Regularization
Jingfeng Wu, Peter L. Bartlett, Sham M. Kakade +2
Existing theory suggests that for linear regression problems categorized by capacity and source conditions, gradient descent (GD) is always minimax optimal, while both ridge regres…
Hard labels sampled from sparse targets mislead rotation invariant algorithms
Avrajit Ghosh, Bin Yu, Manfred Warmuth +1
One of the most common machine learning setups is logistic regression. In many classification models, including neural networks, the final prediction is obtained by applying a logi…
RubiConv -- Efficient Boundary-Respecting Convolutions
Linda Friso, Annie Marsden, Xinyi Chen +4
Convolutional architectures have emerged as powerful alternatives to Transformers for sequence modeling. The primary advantage is that they offer improved theoretical sequence leng…
Training Dynamics of Softmax Self-Attention: Fast Global Convergence via Preconditioning
Gautam Goel, Mahdi Soltanolkotabi, Peter Bartlett
We study the training dynamics of gradient descent in a softmax self-attention layer trained to perform linear regression and show that a simple first-order optimization algorithm…
Large Stepsizes Accelerate Gradient Descent for Regularized Logistic Regression
Jingfeng Wu, Pierre Marion, Peter Bartlett
We study gradient descent (GD) with a constant stepsize for -regularized logistic regression with linearly separable data. Classical theory suggests small stepsizes to ensu…