arXiv research

Majority bit estimation in noisy random recursive DAGs.

One-bit quantization improves inference speed for Random Features models.

Paper improves DNN accelerator robustness against bit errors with energy savings.

The method of random projections has become a standard tool for machine learning, data mining, and search with massive data at Web scale. The effective use of random projections requires efficient coding schemes for quantizing (real-valued) projected data into integers. In this paper, we focus on a simple 2-bit coding …

BEGIN network models binary data without parametric assumptions.

We prove that the binary classifiers of bit strings generated by random wide deep neural networks with ReLU activation function are biased towards simple functions. The simplicity is captured by the following two properties. For any given input bit string, the average Hamming distance of the closest input bit string wi…

New quantization methods improve accuracy of Random Fourier Features.

In this paper, we first demonstrate that b-bit minwise hashing, whose estimators are positive definite kernels, can be naturally integrated with learning algorithms such as SVM and logistic regression. We adopt a simple scheme to transform the nonlinear (resemblance) kernel into linear (inner product) kernel; and hence…

This letter proposes a dictionary learning algorithm for blind one bit compressed sensing. In the blind one bit compressed sensing framework, the original signal to be reconstructed from one bit linear random measurements is sparse in an unknown domain. In this context, the multiplication of measurement matrix $\Ab$ an…

Bit-slice sparsity improves ReRAM-based DNN acceleration.

To improve accuracy and speed of regressions and classifications, we present a data-based prediction method, Random Bits Regression (RBR). This method first generates a large number of random binary intermediate/derived features based on the original input matrix, and then performs regularized linear/logistic regressio…

New memory-query tradeoffs for convex optimization algorithms.

We consider the problem of estimating the arithmetic average of a finite collection of real vectors stored in a distributed fashion across several compute nodes subject to a communication budget constraint. Our analysis does not rely on any statistical assumptions about the source of the vectors. This problem arises as…

New algorithm learns halfspaces over hypercube with random bit flips.

New faster, space-saving methods for subspace embeddings in tensors.

We study the following generalized matrix rank estimation problem: given an $n \times n$ matrix and a constant $c \geq 0$, estimate the number of eigenvalues that are greater than $c$. In the distributed setting, the matrix of interest is the sum of $m$ matrices held by separate machines. We show that any deterministic…

T-BFA targets and misleads specific DNN inputs to a chosen output.

Paper develops an efficient mean estimator for 1-bit communication constraints.

New approach quantifies overfitting in high-dimensional regression.

We generated a dataset of 200 GB with 10^9 features, to test our recent b-bit minwise hashing algorithms for training very large-scale logistic regression and SVM. The results confirm our prior work that, compared with the VW hashing algorithm (which has the same variance as random projections), b-bit minwise hashing i…

Optimal distributed testing under communication constraints with shared randomness.

Paper proposes a 1-bit mean estimation method with near-optimal sample complexity.

New techniques improve 16-bit training accuracy without 32-bit units.

Bayesian Bits unifies quantization and pruning through gradient optimization.

One-bit clustering method for two-component sub-Gaussian mixture models

Low-bit training framework reduces energy consumption in CNNs.

The property of perfectness plays an important role in the theory of Bayesian networks. First, the existence of perfect distributions for arbitrary sets of variables and directed acyclic graphs implies that various methods for reading independence from the structure of the graph (e.g., Pearl, 1988; Lauritzen, Dawid, La…

Diffusion models improve image compression at low bit-rates.

While the channel capacity reflects a theoretical upper bound on the achievable information transmission rate in the limit of infinitely many bits, it does not characterise the information transfer of a given encoding routine with finitely many bits. In this note, we characterise the quality of a code (i. e. a given en…

While deep neural networks are a highly successful model class, their large memory footprint puts considerable strain on energy consumption, communication bandwidth, and storage requirements. Consequently, model size reduction has become an utmost goal in deep learning. A typical approach is to train a set of determini…

The bits-back argument suggests that latent variable models can be turned into lossless compression schemes. Translating the bits-back argument into efficient and practical lossless compression schemes for general latent variable models, however, is still an open problem. Bits-Back with Asymmetric Numeral Systems (BB-A…

Study on recovering supports of multiple sparse vectors from mixed linear measurements.

TRF uses ternary random features to improve ML performance without extra computation.

The state-of-the-art hardware platforms for training Deep Neural Networks (DNNs) are moving from traditional single precision (32-bit) computations towards 16 bits of precision -- in large part due to the high energy efficiency and smaller bit storage associated with using reduced-precision representations. However, un…

Paper proposes a CNN-based method for estimating intra frame bits and quality.

We study a distributed estimation problem in which two remotely located parties, Alice and Bob, observe an unlimited number of i.i.d. samples corresponding to two different parts of a random vector. Alice can send $k$ bits on average to Bob, who in turn wants to estimate the cross-correlation matrix between the two par…

Improves matrix multiplication throughput for asymmetric bit-width operands.

Paper proposes a hybrid model-based and data-driven approach for one-bit compressive autoencoding.

Consider the recovery of an unknown signal ${x}$ from quantized linear measurements. In the one-bit compressive sensing setting, one typically assumes that ${x}$ is sparse, and that the measurements are of the form $\operatorname{sign}(\langle {a}_i, {x} \rangle) \in \{\pm1\}$. Since such measurements give no informati…

Paper proposes a hybrid model-based and data-driven method for one-bit compressive variational autoencoding.

The paper studies the distance from calibration in sequential prediction, proving upper and lower bounds.

New protocols show 1-bit mean estimation can be order-optimal without interaction.

Topological data analysis classifies encrypted bits with success.

We consider the problem of estimating the mean of a symmetric log-concave distribution under the constraint that only a single bit per sample from this distribution is available to the estimator. We study the mean squared error as a function of the sample size (and hence the number of bits). We consider three settings:…

Paper offers robust recovery for 1-bit sensing with partial Gaussian circulant matrices.

In this paper, we use reinforcement learning to find effective decoding strategies for binary linear codes. We start by reviewing several iterative decoding algorithms that involve a decision-making process at each step, including bit-flipping (BF) decoding, residual belief propagation, and anchor decoding. We then ill…

One-bit feedback suffices for a bandit problem's optimal strategy.

New algorithm tackles batched stochastic linear bandits with 1-bit communication constraints.