arXiv research

Polynomial-time DP algorithm for learning Gaussians with matching sample complexity.

Polynomial-time algorithm learns causal graphs without parametric assumptions.

We show that the standard stochastic gradient decent (SGD) algorithm is guaranteed to learn, in polynomial time, a function that is competitive with the best function in the conjugate kernel space of the network, as defined in Daniely, Frostig and Singer. The result holds for log-depth networks from a rich family of ar…

Polynomial-time algorithm learns ReLU networks without assumptions.

Algorithm learns halfspaces with Tsybakov noise in polynomial time.

New algorithm learns decision trees faster than before.

Polynomial-time methods count and sample DAGs from Markov classes.

MAP perturbation models have emerged as a powerful framework for inference in structured prediction. Such models provide a way to efficiently sample from the Gibbs distribution and facilitate predictions that are robust to random noise. In this paper, we propose a provably polynomial time randomized algorithm for learn…

Strongly polynomial algorithm for approximate Forster transforms and halfspace learning.

In this paper we study the adaptive learnability of decision trees of depth at most $d$ from membership queries. This has many applications in automated scientific discovery such as drugs development and software update problem. Feldman solves the problem in a randomized polynomial time algorithm that asks $\tilde O(2^…

This study extends verifiable learning to boosted tree ensembles, enabling efficient security verification.

Polynomial-time tester-learner for general halfspaces with Gaussian adversarial noise.

Robust learning mixtures of linear regressions improve robustness.

We study computational and sample complexity of parameter and structure learning in graphical models. Our main result shows that the class of factor graphs with bounded factor size and bounded connectivity can be learned in polynomial time and polynomial number of samples, assuming that the data is generated by a netwo…

Polynomial-time algorithm for learning halfspaces with Gaussian-distributed data and adversarial noise.

Polynomial-time method solves complex combinatorial semi-bandits.

Polynomial time algorithm matches correlated Gaussian matrices without vanishing correlation.

Polynomial time algorithm learns depth-2 neural networks with ReLU activations.

Simplifies and optimizes learning from untrusted batches with structure.

Polynomial-time methods count and sample DAGs from equivalence classes.

We present the strongest known knot invariant that can be computed effectively (in polynomial time).

Private learning of Gaussian Mixture Models without boundedness assumptions.

Investigates polynomial time algorithms for computing Khovanov homology of braids.

Polynomial-time RL algorithm for constant actions under linear Bellman completeness.

New algorithm for learning ReLU networks with Gaussian noise, improving previous results.

This paper establishes for the first time the predictive performance of speed priors and their computational complexity. A speed prior is essentially a probability distribution that puts low probability on strings that are not efficiently computable. We propose a variant to the original speed prior (Schmidhuber, 2002),…

Decides if elements in free groups are primitive in polynomial time.

Polynomial-time algorithm learns high-dimensional halfspaces without labels.

New algorithm speeds up learning of graphical models.

New polynomial-time solutions found for training ReLU networks, mirroring Max-Cut complexity.

We introduce a new approach for designing computationally efficient learning algorithms that are tolerant to noise, and demonstrate its effectiveness by designing algorithms with improved noise tolerance guarantees for learning linear separators. We consider both the malicious noise model and the adversarial label nois…

Polynomial-time algorithm matches correlated random graphs with non-vanishing correlation.

Quantum machine learning offers advantages for broader learning tasks.

We describe a polynomial-time algorithm to compute a (tight) geodesic between two curves in the curve graph. As well as enabling us to compute the distance between a pair of curves, this has several applications to mapping classes. For example, we can use these geodesics to compute the asymptotic translation length, Ni…

Polynomial-time algorithm for near-optimal community detection in graphs.

New approach verifies tree ensembles efficiently, making them more robust.

The paper provides an almost optimal learning and testing algorithm for sparse polynomials.

Algorithm classifies surface homeomorphisms with polynomial time complexity.

Reduces learning periodic neural networks to lattice problems, proving hardness under cryptographic assumptions.

The problem of high-dimensional path-dependent optimal stopping (OS) is important to multiple academic communities and applications. Modern OS tasks often have a large number of decision epochs, and complicated non-Markovian dynamics, making them especially challenging. Standard approaches, often relying on ADP, dualit…

We consider the problem of learning a causal graph over a set of variables with interventions. We study the cost-optimal causal graph learning problem: For a given skeleton (undirected version of the causal graph), design the set of interventions with minimum total cost, that can uniquely identify any causal graph with…

New algorithm recovers sparse measures in polynomial time.

Detecting correlated trees helps align sparse graphs.

Efficiently learns polytrees with known skeleton in polynomial time and sample complexity.

EKM solves the K-medoids problem in polynomial time.

This work finds a point with small test error in polynomial time for mildly overparameterized neural nets.

Low-degree method fails to predict robust subspace recovery problem.

Adam optimizes linear classifiers with separable data.