arXiv research

New framework captures long-term decision dependence in online learning.

New algorithms for streaming bandits with limited memory.

Study reduces memory needs for active learning with enriched queries.

Quantum memory limits set by relativity theory.

Combinatorial dimensions play an important role in the theory of machine learning. For example, VC dimension characterizes PAC learning, SQ dimension characterizes weak learning with statistical queries, and Littlestone dimension characterizes online learning. In this paper we aim to develop combinatorial dimensions th…

The study analyzes prediction errors in systems with memory kernels, providing bounds and stability results.

Study non-oblivious adversarial bandits with delayed feedback and propose algorithms with improved regret bounds.

New analysis tightens memory capacity of Hopfield models using spherical codes.

We show that fundamental learning tasks, such as finding an approximate linear separator or linear regression, require memory at least \emph{quadratic} in the dimension, in a natural streaming setting. This implies that such problems cannot be solved (at least in this setting) by scalable memory-efficient streaming alg…

We analyze computational limits of modern Hopfield models based on pattern norms.

Memory-constrained algorithms need superlinear memory for efficient convex optimization.

Study language generation with limited memory, showing different impacts on achievable densities and convergence.

Improved single-pass streaming MAB regret bound to O(K^1/3T^2/3).

Memory-augmented neural networks consisting of a neural controller and an external memory have shown potentials in long-term sequential learning. Current RAM-like memory models maintain memory accessing every timesteps, thus they do not effectively leverage the short-term memory held in the controller. We hypothesize t…

Deep learning typically requires training a very capable architecture using large datasets. However, many important learning problems demand an ability to draw valid inferences from small size datasets, and such problems pose a particular challenge for deep learning. In this regard, various researches on "meta-learning…

Generalizes memory and forecasting capacities for nonlinear recurrent networks with dependent inputs.

Survey on statistical inference under memory constraints.

Quadratic memory is essential for optimal convex optimization queries.

New algorithms for multitask learning with long-term memory.

PySAD offers a unified Python framework for efficient streaming anomaly detection.

Gradient descent is efficient for solving feasibility problems with minimal memory and queries.

A new optimization method handles Euclidean bounds efficiently.

Paper studies statistical-computational trade-offs in tensor PCA and related problems.

We propose a new method to study the internal memory used by reinforcement learning policies. We estimate the amount of relevant past information by estimating mutual information between behavior histories and the current action of an agent. We perform this estimation in the passive setting, that is, we do not interven…

New algorithm reduces memory usage for multi-pass bandit problems.

The analysis of Belief Propagation and other algorithms for the {\em reconstruction problem} plays a key role in the analysis of community detection in inference on graphs, phylogenetic reconstruction in bioinformatics, and the cavity method in statistical physics. We prove a conjecture of Evans, Kenyon, Peres, and Sch…

Algorithm learns linear systems from partial observations with near-optimal rate.

A new method stabilizes deep reinforcement learning by using QGraphs to retain replay memory information.

Paper introduces a new framework to improve sample efficiency in POMDPs learning.

A central challenge faced by memory systems is the robust retrieval of a stored pattern in the presence of interference due to other stored patterns and noise. A theoretically well-founded solution to robust retrieval is given by attractor dynamics, which iteratively clean up patterns during recall. However, incorporat…

Recent studies on automatic neural architectures search have demonstrated significant performance, competitive to or even better than hand-crafted neural architectures. However, most of the existing network architecture tend to use residual, parallel structures and concatenation block between shallow and deep features …

We derive upper and lower bounds for the policy regret of $T$-round online learning problems with graph-structured feedback, where the adversary is nonoblivious but assumed to have a bounded memory. We obtain upper bounds of $\widetilde O(T^{2/3})$ and $\widetilde O(T^{3/4})$ for strongly-observable and weakly-observab…

We study the power of different types of adaptive (nonoblivious) adversaries in the setting of prediction with expert advice, under both full-information and bandit feedback. We measure the player's performance using a new notion of regret, also known as policy regret, which better captures the adversary's adaptiveness…

The memory capacity of linear echo state networks is accurately calculated using new numerical methods.

Analyzed a generalized voter model with power-law herding intensity, revealing anomalous diffusion and long-range memory.

We study distribution testing with communication and memory constraints in the following computational models: (1) The {\em one-pass streaming model} where the goal is to minimize the sample complexity of the protocol subject to a memory constraint, and (2) A {\em distributed model} where the data samples reside at mul…

Nonlinear RNNs' memory capacity varies widely, making it impractical.

Efficient algorithm predicts unknown linear systems with long-term memory.

Study shows how to balance memory and learning efficiency in continual learning.

In this paper, we study the generalization properties of online learning based stochastic methods for supervised learning problems where the loss function is dependent on more than one training sample (e.g., metric learning, ranking). We present a generic decoupling technique that enables us to provide Rademacher compl…

We consider the problem of performing linear regression over a stream of $d$-dimensional examples, and show that any algorithm that uses a subquadratic amount of memory exhibits a slower rate of convergence than can be achieved without memory constraints. Specifically, consider a sequence of labeled examples $(a_1,b_1)…

A new method speeds up spectral normalization for neural nets.

Sparse Hopfield model improves memory retrieval with fewer connections.

We consider streaming, one-pass principal component analysis (PCA), in the high-dimensional regime, with limited memory. Here, $p$-dimensional samples are presented sequentially, and the goal is to produce the $k$-dimensional subspace that best approximates these points. Standard algorithms require $O(p^2)$ memory; mea…

A new associative memory uses Sinkhorn divergence for efficient pattern retrieval.

TASO optimizes CNN models for memory-constrained devices.

Improved deep learning model deployment on tiny MCUs with mixed-precision quantization.

We propose the first reduction-based approach to obtaining long-term memory guarantees for online learning in the sense of Bousquet and Warmuth, 2002, by reducing the problem to achieving typical switching regret. Specifically, for the classical expert problem with $K$ actions and $T$ rounds, using our framework we dev…