Generative adversarial networks (GANs) are promising for a range of applications, including image translation and denoising, as well as synthetic data generation. These applications can be mapped to memristive crossbar arrays (MCAs) for ultra-high energy efficiency and portability. However, conductance variation within analog crossbars degrades the quality of the GAN outputs and necessitates robust post-manufacturing testing. We propose a two-stage adaptive test framework for compute-in-memory (CiM) based GANs, comprising an exhaustive test and a compact test. The exhaustive test measures the inception score of a device under test (DUT) by applying a large number of noise vectors, called the exhaustive noise set. To reduce test time, a compact test estimates the inception score of a DUT from a carefully chosen subset of these vectors, called the compact noise set. The compact noise set is determined by a binary mask optimized with a novel backpropagation-guided algorithm to minimize the difference between the estimated and true inception scores of the DUTs. Finally, to leverage both the accuracy of the exhaustive test and the speed of the compact test, the proposed adaptive test framework first applies the compact test to every DUT. Only the DUTs that yield low confidence in classifications are then subjected to the exhaustive test. Experiments show that this adaptive approach achieves less than 1% test escapes while offering up to 7.26× speedup compared to exhaustive test.

Computing the Fourier transform of a q-ary function $f:\mathbb{Z}_q^n \to {\mathbb{R}}$, which maps q-ary sequences to real numbers, is an important problem in mathematics with wide-ranging applications in biology, signal processing, and machine learning. Previous studies have shown that, under the sparsity assumption, the Fourier transform can be computed efficiently using fast and sample-efficient algorithms. However, in most practical settings, the function is defined over a more general space—the space of generalized q-ary sequences ${\mathbb{Z}_{{q_1}}} \times {\mathbb{Z}_{{q_2}}} \times \cdots \times {\mathbb{Z}_{{q_n}}}$ — where each ${\mathbb{Z}_{{q_i}}}$ corresponds to integers modulo qi. Herein, we develop GFast, a coding theoretic algorithm that computes the S-sparse Fourier transform of f with a sample complexity of O(Sn), computational complexity of O(SnlogN), and a failure probability that approaches zero as $N = \prod\nolimits_{i = 1}^n {{q_i}} \to \infty $ with S = Nδfor some 0 ≤ δ2) and computational complexity of O(Sn2logN) under the same high probability guarantees. Additionally, we demonstrate that GFast computes the sparse Fourier transform of generalized q-ary functions 8× faster using 16× fewer samples on synthetic experiments, and enables explaining real-world heart disease diagnosis and protein fitness models using up to 13× fewer samples compared to existing Fourier algorithms applied to the most efficient parameterization of the models as q-ary functions.

The growing adoption of machine learning models for biological sequences has intensified the need for interpretable predictions, with Shapley values emerging as a theoretically grounded standard for model explanation. While effective for local explanations of individual input sequences, scaling Shapley-based interpretability to extract global biological insights requires evaluating thousands of sequences—incurring exponential computational cost per query. We introduce SHAP zero, a novel algorithm that amortizes the cost of Shapley value computation across large-scale biological datasets. After a one-time model sketching step, SHAP zero enables near-zero marginal cost for future queries by uncovering an underexplored connection between Shapley values, high-order feature interactions, and the sparse Fourier transform of the model. Applied to models of guide RNA efficacy, DNA repair outcomes, and protein fitness, SHAP zero explains predictions orders of magnitude faster than existing methods, recovering rich combinatorial interactions previously inaccessible at scale. This work opens the door to principled, efficient, and scalable interpretability for black-box sequence models in biology.

Autoregressive models have transformed protein engineering by enabling the generation of novel protein sequences beyond those found in nature. However, their sequential inference introduces significant latency, limiting their utility in high-throughput protein screening. Speculative decoding accelerates generation by employing a lightweight draft model to sample tokens, which a larger target model then verifies and refines. Yet in protein sequence generation, draft models are typically agnostic to the structural and functional constraints of the target protein, leading to biologically implausible outputs and a shift in the likelihood distribution of generated sequences. We introduce SpecMER (Speculative Decoding via k-mer Guidance), a novel framework that incorporates biological, structural, and functional priors using k-mer motifs extracted from multiple sequence alignments. By scoring candidate sequences in parallel and selecting those most consistent with known biological patterns, SpecMER significantly improves sequence plausibility while retaining the efficiency of speculative decoding. SpecMER achieves 24–32% speedup over standard autoregressive decoding, along with higher acceptance rates and improved sequence likelihoods.

Fourier transformations of pseudo-Boolean functions are popular tools for analyzing functions of binary sequences. Real-world functions often have structures that manifest in a sparse Fourier transform, and previous works have shown that under the assumption of sparsity the transform can be computed efficiently. But what if we want to compute the Fourier transform of functions defined over a q-ary alphabet? These types of functions arise naturally in many areas including biology. A typical workaround is to encode the q-ary sequence in binary however, this approach is computationally inefficient and fundamentally incompatible with the existing sparse Fourier transform techniques. Herein, we develop a sparse Fourier transform algorithm specifically for q-ary functions of length n sequences, dubbed q-SFT, which provably computes an S-sparse transform with vanishing error as qn→ ∞ in O(Sn) function evaluations and O(Sn2log q) computations, where S = qnδfor some δ2) and a computational complexity of O(Sn3) with the same asymptotic guarantees. We present numerical simulations on synthetic and real-world RNA data, demonstrating the scalability of q-SFT to massively high dimensional q-ary functions.

SUMMARY: We propose a new spectral framework for reliable training, scalable inference and interpretable explanation of the DNA repair outcome following a Cas9 cutting. Our framework, dubbed CRISPRL and, relies on an unexploited observation about the nature of the repair process: the landscape of the DNA repair is highly sparse in the (Walsh-Hadamard) spectral domain. This observation enables our framework to address key shortcomings that limit the interpretability and scaling of current deep-learning-based DNA repair models. In particular, CRISPRL and reduces the time to compute the full DNA repair landscape from a striking 5230 years to 1 week and the sampling complexity from 1012 to 3 million guide RNAs with only a small loss in accuracy (R2R2 ∼ 0.9). Our proposed framework is based on a divide-and-conquer strategy that uses a fast peeling algorithm to learn the DNA repair models. CRISPRL and captures lower-degree features around the cut site, which enrich for short insertions and deletions as well as higher-degree microhomology patterns that enrich for longer deletions. AVAILABILITY AND IMPLEMENTATION: The CRISPRL and software is publicly available at https://github.com/UCBASiCS/CRISPRLand.

Sensor selection refers to the problem of intelligently selecting a small subset of a collection of available sensors to reduce the sensing cost while preserving signal acquisition performance. The majority of sensor selection algorithms find the subset of sensors that best recovers an arbitrary signal from a number of linear measurements that is larger than the dimension of the signal. In this paper, we develop a new sensor selection algorithm for sparse (or near sparse) signals that finds a subset of sensors that best recovers such signals from a number of measurements that is much smaller than the dimension of the signal. Existing sensor selection algorithms cannot be applied in such situations. Our proposed Incoherent Sensor Selection (Insense) algorithm minimizes a coherence-based cost function that is adapted from recent results in sparse recovery theory. Using three datasets, including a real-world dataset on microbial diagnostics, we demonstrate the superior performance of Insense for sparse-signal sensor selection.

Feature selection is an important challenge in machine learning. It plays a crucial role in the explainability of machine-driven decisions that are rapidly permeating throughout modern society. Unfortunately, the explosion in the size and dimensionality of real-world datasets poses a severe challenge to standard feature selection algorithms. Today, it is not uncommon for datasets to have billions of dimensions. At such scale, even storing the feature vector is impossible, causing most existing feature selection methods to fail. Workarounds like feature hashing, a standard approach to large-scale machine learning, helps with the computational feasibility, but at the cost of losing the interpretability of features. In this paper, we present MISSION, a novel framework for ultra large-scale feature selection that performs stochastic gradient descent while maintaining an efficient representation of the features in memory using a Count-Sketch data structure. MISSION retains the simplicity of feature hashing without sacrificing the interpretability of the features while using only O(log^2(p)) working memory. We demonstrate that MISSION accurately and efficiently performs feature selection on real-world, large-scale datasets with billions of dimensions.

Hashing is an important tool in large-scale machine learning. Unfortunately, current data-dependent hashing algorithms are not robust to small perturbations of the data points, which degrades the performance of nearest neighbor (NN) search. The culprit is the minimization of the L_2-norm, average distortion among pairs of points to find the hash function. Inspired by recent progress in robust optimization, we develop a novel hashing algorithm, dubbed RHash, that instead minimizes the L_1-norm, worst-case distortion among pairs of points. We develop practical and efficient implementations of RHash that couple the alternating direction method of multipliers (ADMM) framework with column generation to scale well to large datasets. A range of experimental evaluations demonstrate the superiority of RHash over ten state-of-the-art binary hashing schemes. In particular, we show that RHash achieves the same retrieval performance as the state-of-the-art algorithms in terms of average precision while using up to 60% fewer bits.

Optimization has been used extensively throughout signal processing in applications including sensor networks and sparsity based compressive sensing. One of the key challenges when implementing iterative optimization algorithms is to choose an appropriate step size for fast algorithms. We pose the problem of choosing step sizes as solving a ski rental problem, a popular class of problems from the computer science literature. This results in a novel algorithm for adaptive step size selection that is agnostic to the choice of the optimization algorithm. Our numerical results show the advantages of using adaptivity for step size selection.