We continue the investigation into the power of smaller Transformer-base...
Employing Large Language Models (LLMs) to address mathematical problems ...
Large Language Models (LLMs) have shown impressive performance as genera...
Given a convex function f on ℝ^n with an integer minimizer, we
show how ...
Artificial intelligence (AI) researchers have been developing and refini...
Fine-tuning a language model on a new domain is standard practice for do...
The development of efficient sampling algorithms catering to non-Euclide...
We introduce a new tool for stochastic convex optimization (SCO): a
Rewe...
Existing analyses of neural network training often operate under the
unr...
The simplex method for linear programming is known to be highly efficien...
We study the convergence rate of discretized Riemannian Hamiltonian Mont...
We refine the recent breakthrough technique of Klartag and Lehec to obta...
Many fundamental problems in machine learning can be formulated by the c...
We propose a new framework for differentially private optimization of co...
Large pretrained models can be privately fine-tuned to achieve performan...
We present a nearly-linear time algorithm for finding a minimum-cost flo...
In this paper, we study private optimization problems for non-smooth con...
We demonstrate for the first time that ill-conditioned, non-smooth,
cons...
We make several advances broadly related to the maintenance of electrica...
We present an algorithm for computing approximate ℓ_p Lewis weights to
h...
We give simpler, sparser, and faster algorithms for differentially priva...
We give a short, self-contained proof of the interior point method and i...
We give lower bounds on the performance of two of the most popular sampl...
We give a fast algorithm to optimally compose privacy guarantees of
diff...
We study the differentially private Empirical Risk Minimization (ERM) an...
Differentially Private-SGD (DP-SGD) of Abadi et al. (2016) and its varia...
In this paper we provide new randomized algorithms with improved runtime...
Arising from structural graph theory, treewidth has become a focus of st...
We give algorithms for sampling several structured logconcave families t...
Semidefinite programs (SDPs) are a fundamental class of optimization pro...
We present an Õ(m+n^1.5)-time randomized algorithm for maximum
cardinali...
We show that the the volume of a convex body in ℝ^n in the
general membe...
We consider sampling from composite densities on ℝ^d of the form
dπ(x) ∝...
In 1988, Eric B. Baum showed that two-layers neural networks with thresh...
Given a separation oracle for a convex set K ⊂R^n that is
contained in a...
Consider an oracle which takes a point x and returns the minimizer of a
...
We give the first approximation algorithm for mixed packing and covering...
We show that the gradient norm ∇ f(x) for x ∼(-f(x)),
where f is strongl...
In this paper we provide an Õ(nd+d^3) time randomized algorithm
for solv...
In this paper we consider the classic matroid intersection problem: give...
Motivated by the Dikin walk, we develop aspects of an interior-point the...
The Circle Packing Theorem states that every planar graph can be represe...
We present an algorithm that given a linear program with n variables, m
...
Sampling from log-concave distributions is a well researched problem tha...
A landmark result of non-smooth convex optimization is that gradient des...
We develop a simple and efficient algorithm for approximating the John
E...
Many convex problems in machine learning and computer science share the ...
We study semidefinite programs with diagonal constraints. This problem c...
Sampling logconcave functions arising in statistics and machine learning...
In our recent work (Bubeck, Price, Razenshteyn, arXiv:1805.10204) we arg...