Searcharxiv⌕ Search

arXiv subjects

Aritra Das

Publications and source records attributed to Aritra Das.

At least 19 recordsLinked to original sources

What's in a Tree ? Hierarchical $n$-gram models as controlled approximators of language

Hierarchical models have been proposed as synthetic settings for studying language. However, their relevance to realistic language corpora remains underexplored. In this work, we introduce tree-grams, autoregressive generative $n$-gram models that build the conditional probability tensor $p(x_n \mid x_{1:n-1})$ through a hierarchical composition of order-2 and order-3 tensors. $n$ controls the maximal context window, whereas a rank hyperparameter $d$ controls model capacity, yielding an interpretable and systematically scalable family of approximators of language. We show how tree-grams outperform existing $n$-gram baselines, while remaining competitive with deep transformer-based language models. We demonstrate the utility of such controlled approximations by using tree-grams as generative models. In particular, we show that hyperparameter transfer under $μ$P can be made more robust when narrower models are tuned on simpler data, generated by tree-grams with moderate $n$ and $d$. In addition, we show that entropy and effective range of correlations control performance gap after fine-tuning. This is because tree-grams allow us to explicitly control horizon and capacity. When allowed to route across candidate topologies, we observe emergent sparsity in tree-grams. Such concentrated routing permits pruning upto 95\% of topologies without significant change in performance.

cs.CL↗

Delegating Computation with Approximate Arithmetic: Interactive Proofs for Wizards

We study interactive proofs for arithmetic circuits over the complex numbers $\mathbb{C}$ in which both the prover and the verifier compute approximately (unlike muggles, wizards can use magic, i.e., floating-point numbers). The goal is to prove that a claimed output $y$ is close to the exact output $C(x)$: for thresholds $0<Δ_0<Δ$, the honest prover is accepted whenever $|y-C(x)|\leΔ_0$, and every prover is rejected with high probability whenever $|y-C(x)|>Δ$. Existing proof systems for real-valued data verify rounded finite-field computations. Bitan et al.~[EUROCRYPT~2026] gave an approximate sum-check protocol. We extend the protocol of Goldwasser, Kalai, and Rothblum (GKR) [STOC~2008] to public-coin interactive proofs for logspace-uniform layered circuits over $\mathbb{C}$ of size $S$, depth $L$, and $n$ inputs, under public bounds on gate values and wiring coefficients. At constant soundness error, the verifier runs in time $(n+1)\mathrm{poly}(L,\log S,b)$, the communication is $\mathrm{poly}(L,\log S,b)$, and the prover runs in time $\mathrm{poly}(S,b)$, where $b$ is the bit precision. To the best of our knowledge, these are the first doubly efficient interactive proofs in which both parties compute approximately. GKR reduces two claims about a layer to one on a random line, which leaves the unit circle, where our error bounds hold. We instead label gates by complex roots of unity and combine the two claims with a random root of unity as coefficient. We choose the error thresholds backward from the input layer, so that a large output error survives the verifier's rounding at every step. The honest prover needs only $O(S \log S)$ complex operations. We also obtain zero-knowledge proofs from one-way functions, one-round arguments from private information retrieval, and interactive PCPs whose proof length is polynomial in the witness length.

cs.CR↗

HomID : Benchmarking Intrinsic Dimension Estimators on Homogenous Manifolds with Anisotropic Embeddings

The manifold hypothesis suggests that data lies on manifolds with smaller intrinsic dimension (ID) than their ambient dimension. However there is no empirical agreement on the estimates for ID from different estimators for realistic datasets. Thus it is important to test ID estimators (IDEs) with targeted stressors. In this work, we consider the role of anisotropy. To this end, we propose HomID, a collection of homogeneous spaces with anisotropic embedding, for benchmarking ID estimators. We observe that methods that perform well on standard benchmarks systematically degrade on HomID under identical resource allocation. We further observe that anisotropic distortion of such benchmarks also results in performance degradation. Finally, we demonstrate that controlled anisotropic distortions induce systematic shifts in the distributions on which these methods rely, providing a concrete mechanism for the resulting estimation errors in two particular IDEs. The code for the project is available at https://github.com/a-writes-code/homid

cs.LG↗

On the Indistinguishability of Human v/s AI Generated Text

The rapid improvement of LLMs has made distinguishing AI-generated text from human writing a pressing problem. This challenge is further amplified by paraphrasing tools designed to make machine-generated text appear more ``human''. We study how access to human writing samples can be used to strategically paraphrase machine-generated responses toward the human distribution. Under a multi-sample setting with human and machine responses to the same prompts, we show that repeated paraphrasing moves the machine distribution toward a human target under mixing and stability conditions. We derive an explicit convergence rate, examine how semantic-preservation and quality constraints affect this rate, and extend the analysis to finite samples to characterize how the required human data and paraphrasing rounds scale with the desired error. We extend the analysis beyond the shared-parameter setting by learning a human-preserving rewriting kernel.

cs.LG↗

You Can't Escape Your Activations : Evaluation Awareness and Multi-Agent Monitoring

LLM agents are increasingly deployed in multi-agent systems, where they can collude while keeping their actions benign. Output monitors designed to detect such collusions can be fooled by obfuscation and steganography, motivating the use of probes trained on internal activations. However, these probes are usually evaluated on agents that do not know they are being watched. We study how activation-based detection changes when agents are explicitly informed that their internal activations are being monitored, and when they additionally receive feedback from the monitor. We keep the models, probes, and thresholds fixed and change only what the agents are told: nothing (baseline), that an activation monitor is present (aware), or that a monitor is present together with the previous round's score (feedback). We test two games, a four-agent blackjack game and a two-agent Simmons prisoners game, using Qwen3-32B-AWQ and GPT-OSS-20B in homogeneous and mixed pairings. Telling agents about the monitor does not hide them. The best probes stay accurate in all three conditions, and the agents keep colluding.

cs.MA↗

Parameterized Complexity of $L_p$-Lipschitz Constants for Input Convex Neural Networks and $L_p$-Norm Maximization over Zonotopes

Lipschitz constants are a standard way to quantify the sensitivity of neural networks to small input perturbations, but computing them is difficult even for shallow ReLU networks. We study this problem for two-layer input-convex neural networks (ICNNs), a restricted architecture where nonnegative output weights enforce convexity. Computing the $L_p$-Lipschitz constant for these networks is equivalent to maximizing the dual norm over a zonotope. While $L_1$- and $L_\infty$-norm maximization on zonotopes admit fixed-parameter and polynomial-time algorithms, respectively, the parameterized complexity of the remaining $L_p$-norms was open. We prove that, for every fixed $p\in (1,\infty)\cap \mathbb{Q}$, maximizing the $L_p$-norm over a zonotope in $\mathbb{R}^d$ is W[1]-hard with respect to the dimension $d$. Moreover, our hardness results imply that brute-force enumeration algorithms are essentially optimal for this problem under the Exponential Time Hypothesis. By duality, the same hardness results hold for computing the $L_p$-Lipschitz constant of two-layer ReLU ICNNs. Our proof first establishes the result for the $L_2$-norm and then transfers the construction to arbitrary fixed $p\in (1,\infty)\cap\mathbb{Q}$ using a suitable Taylor approximation. These results resolve the corresponding questions regarding the parameterized complexity status for zonotope norm maximization and two-layer ICNN Lipschitz constants. Our paper resolves an open problem posted at COLT'25. There are several independent concurrent papers resolving the same problem. Our paper prioritizes a clear exposition of the underlying mathematics and conceptual intuitions behind the proof. Additionally, we explicitly describe our research process including the use of LLMs.

cs.CC↗

Super-Exponential Advantage of Squeezed Light in Phase Estimation under Discrete Phase Randomisation

A paradigmatic task in quantum metrology is that of phase estimation. For this task it is commonly believed, under reasonable assumptions about prior information, that a quadratic advantage in sensitivity is the maximum possible advantage offered by the use of quantum resources. In this work, we consider a channel that implements a phase shift by an angle $2πk/M$, where $k$ is a uniformly random unknown integer, in addition to a small unknown phase shift of interest. We show that, subject to a constraint on the mean photon number per channel use, there is a super-exponential separation between the quantum Fisher information (QFI) attainable using a squeezed vacuum state and that attainable using coherent states. This advantage holds over any state obtained from a coherent state via phase covariant channels. Specifically, when the mean photon number per channel use is 1, the ratio of their QFI grows as $Ω[(M/\sqrt{2}e)^M]$. For a mean photon number per channel use of $M/\log(M)$, the squeezed vacuum QFI is $Ω(M^{3/2}/\sqrt{\log(M)})$, whereas for a coherent state it is at most $\exp[-M\log\log(M)+O(M)]$. We complement this QFI analysis with non-asymptotic estimation results. For a mean photon number per channel use of $M/\log M$, an explicit squeezed-vacuum protocol estimates the phase to accuracy $O(1/M)$ using $O(\sqrt{M\log M})$ channel uses, whereas every coherent state protocol requires at least $\exp[M\log\log M-O(M)]$ channel uses. We consider the effects of noise and show that the ratio of their QFIs can still grow super-exponentially in $M$. Finally, under fixed optical loss and thermal noise, choosing $\bar n=M^2/(\log M)^{3/2}$ allows squeezed vacuum with heterodyne detection to achieve accuracy $O(1/M)$ using sub-polynomially many channel uses, whereas every protocol in the specified classical family requires super-polynomially many.

quant-ph↗

Deciding the Attainability of the Multiparameter Quantum Fisher Information is NP-Hard

The quantum Fisher information (QFI) sets a fundamental bound on the attainable precision when estimating multiple parameters simultaneously. Incompatibility among the individually optimal measurements can, in some cases, imply that the precision limit set by the QFI is not attainable. In certain special cases, including pure states and full-rank states, the exact conditions for when the precision limit set by the QFI can be saturated are known. However, general conditions for the attainability of the QFI with measurements on individual copies of the quantum state have long been sought. Indeed, this was recently stated as one of the five problems in quantum information theory highlighted by [P. Horodecki et al, PRX Quantum 3, 010101 (2022)]. In this work we prove that exact attainability with individual measurements is NP-hard to decide, even for a restricted set of real, constant-rank quantum models. The source problem for our proof is the NP-hard problem of deciding whether a given bipartite density matrix is separable or not. Our result shows that the longstanding difficulty in obtaining general conditions for QFI attainability reflects a fundamental computational obstruction, rather than merely a limitation of existing mathematical techniques: unless P=NP, no efficiently computable necessary-and-sufficient criterion can exist in general.

quant-ph↗

Quantum advantage in learning single mode bosonic channels

Quantum resources can dramatically reduce the data required to learn physical systems, with exponential improvements in sample complexity demonstrated in several quantum learning tasks. However, these advantages have typically relied on quantum resources that scale with problem complexity, most notably increasing system dimension or entanglement. This raises a fundamental question: can exponential quantum learning advantages arise within a fixed, unentangled quantum system? In this paper, we address this question by considering the learning of an unknown random-displacement distribution whose complexity is determined not by the dimensionality of the physical system, but by the Fourier resolution of its features. We show that the quantum-limited noise of vacuum probes progressively obscures high-frequency features, leading to an exponential growth in sample complexity. We establish an information-theoretic lower bound for arbitrary classical-state probes and show that squeezing overcomes this classical limit by extending the accessible Fourier bandwidth. Experimentally, we demonstrate an exponential reduction in sample complexity using squeezed vacuum probes for both binary hypothesis testing and characteristic-function reconstruction. Our results show that a single bosonic mode can exhibit exponential quantum learning advantages without entanglement or an increase in system size, identifying accessible Fourier bandwidth as a fundamentally distinct resource for quantum-enhanced learning.

quant-ph↗

Near-Optimal Bell Nonlocality with GKP and Entangled Cat States

Gottesman-Kitaev-Preskill (GKP) states are widely studied as a bosonic encoding for fault-tolerant quantum computing because small displacement errors can be identified and corrected through syndrome measurements. However, fault-tolerant operation requires substantially greater GKP squeezing than is currently available in optical platforms. It is therefore important to identify quantum-information tasks that can be realised with finite-squeezing GKP states. Here, we study Bell nonlocality in finite-energy GKP Bell states under experimentally motivated measurement constraints. Although finite-energy GKP Bell states support Bell nonlocality even at low squeezing, logical Pauli measurements alone cannot reveal it. Accessing the maximum CHSH violation supported by the state generally requires logical non-Clifford rotations. We instead show that the required non-Gaussian resource can reside in the measurement itself. Photon-number-resolving detection combined with Gaussian preprocessing and adaptive feed-forward closely approaches the maximum violation of the CHSH Bell inequality without implementing logical non-Clifford gates. The same measurement principle strongly enhances Bell violations for cat-code Bell pairs and entangled coherent states, demonstrating that its usefulness extends beyond the GKP lattice. Our results identify non-Gaussian measurements as a practical route to revealing Bell nonlocality in finite-energy bosonic states.

quant-ph↗

Symmetries and Singularities

Deep neural networks are highly over-parameterized, and different parameter values represent the same predictive function. This makes their effective complexity difficult to measure using only the number of parameters or the rank of the Hessian. Singular Learning Theory addresses this issue through the local learning coefficient (LLC), which characterizes the effective complexity of a model near a given solution. Existing methods for estimating the LLC often rely on posterior sampling, which can be computationally expensive for large neural networks. This makes accurate LLC estimation difficult at scale. In this work, we use known structures in the model to simplify the analysis and make LLC estimation more tractable. Specifically, we study the LLC of a graph attention model by exploiting symmetries in both the graph structure and the attention parameters. An analytic framework through a teacher--student setting, and explicit LLC estimates after considering the symmetry--induced degeneracies are developed.

cs.LG↗

The Query Knows What to Forget: A Second Erase Direction for Linear Attention

Linear attention keeps a state of fixed size. At long context, many stored items share this state, and interference between them degrades retrieval. Gated DeltaNet-2 (GDN-2), like every delta-rule model before it, derives its erase vector from the key of the current token. However, the interference in its reads is measured through the query, and the erase step cannot reach it. We introduce the Query-derived Erase Direction (QED). QED adds a second erase direction derived from the query and orthogonal to the key. In the fast-weight view, a key-directed delta edit cannot change the key-orthogonal part of a read. It uses the editable part to cancel old-state content measured along the query. It also improves retrieval at every length past the training window, and it about doubles the usable context length on S-NIAH-1.

cs.LG↗

Linearized 2-Simplicial Attention

We present a linearized form of 2-simplicial attention by rewriting the trilinear score as an inner product between a composite query and a key, so that the sum over one token axis takes the same form as ordinary softmax attention. We then approximate this sum with positive random features and store the entire past in a fixed-size state, while the second axis stays explicit over a short window of recent tokens. This enables us to achieve linear cost in sequence length combined with a global reach that windowed 2-simplicial attention lacks. We implement it with custom Triton kernels and combine it with Kimi Delta Attention to build a model with no softmax attention at all. Under matched compute, this model achieves the highest mean downstream accuracy among the compared architectures, and at 16k context it improves mean accuracy over a KDA hybrid while lowering LAMBADA perplexity from 715.6 to 602.6.

cs.AI↗

Identifying Intelligent Processes via Online Sequential Testing

Active sequential hypothesis testing studies how to identify an unknown hypothesis with a given set of sensing actions. We study this in the setting of identifying large language models (LLMs), \textit{i.e.}, if a user is conversing with an LLM drawn from a known set of models, how can they identify which one is in use? Here, the available sensing actions (evaluations) are themselves a design choice: an evaluator must first decide which environments and prompt families to construct, and only then decide how to use them sequentially. We formalize these two levels as an outer probe-design problem and an inner identification problem. Simply put, the outer stage selects a set of probes to be sent to the entire set of models, creating a kind of fingerprint dataset. This is followed by the inner stage, which sequentially sends a budget-minimizing set of those probes to identify the model in use. For the outer problem, we show that selecting which evaluations to construct at minimum cost, so that every pair of candidates is distinguished, is exactly a weighted set cover problem. Since the response distributions of the candidate models are not known exactly but only through calibration samples, we give a one-shot procedure that estimates the cover instance from these samples. For the inner problem, we bound the number of evaluations needed to identify the unknown model in terms of how well the available evaluations distinguish each pair of candidates.

cs.AI↗

A Rate Separation for Agnostic Direct Sums

Hanneke, Moran, and Waknine \cite{HannekeMoranWaknine2024} asked how the agnostic PAC learning curve of the direct sum $C^r$ depends on the single-instance learning curve $\epsagn(n\mid C)$ and on $r$. We show that the single-instance learning rate does not determine the direct-sum rate. Let $\F$ be the class of the two constant binary functions and let $\G$ consist of the zero function and the identity function. Both classes have agnostic learning curve of order $n^{-1/2}$.

cs.LG↗

Who Belongs in the Eval Set? A Capability-Taxonomy-Driven Pipeline for Curating Regression Eval Sets in Agent-Extensibility Platforms

Platform teams hosting agent-extensibility surfaces face a regression-economics paradox: every onboarding customer ships an evaluation set tuned to their domain, but the platform's regression set must live under a hard query-count ceiling bounded by release cadence. To our knowledge, no published industrial pipeline addresses this platform-side curation problem: existing evaluation frameworks are customer-side, and benchmark-compression work treats benchmarks as fixed pools rather than streams of incoming sets. We describe a capability-taxonomy-driven curation pipeline applied to declarative agents with custom actions in Microsoft 365 Copilot. It takes an agent specification and a customer's eval set as input, projects each query into a platform-owned capability taxonomy, and outputs per-query decisions (admit, drop, swap, or human review), under the philosophy that a healthy regression set is the minimal set of queries capturing the maximal spread of capability signatures -- distinct combinations of capabilities a query exercises together. Three components instantiate this: a classifier producing per-(query, capability) verdicts via a hybrid of deterministic specification-based extraction and large-language-model (LLM) semantic inference; an Invocation Quality (IQ) rater scoring how thoroughly a query exercises each capability, so a new query sharing a signature with an existing entry can still be recognized as a better test and displace it; and a consolidator comparing incoming queries against the regression set on coverage and quality through a rule-based decision cascade, backed by a conservative curator that only suggests evictions. The mechanism is taxonomy-agnostic and applies to any regression eval-set curation problem with a typed capability taxonomy, including taxonomies that evolve in response to the very evidence the pipeline surfaces.

cs.LG↗

Joint 3D Gravity and Magnetic Inversion via Rectified Flow and Ginzburg-Landau Guidance

Subsurface ore detection is of paramount importance given the rising depletion of shallow mineral resources in recent years. It is crucial to explore approaches that go beyond the limitations of traditional geological exploration methods. Due to readily available surface readings, joint magnetic and gravitational inversion is a promising new method - given magnetic and gravitational data on a surface, jointly reconstructing the underlying densities that generate them. However, this is ill-posed and has non-unique solutions. Deterministic methods often require handcrafted priors and converge to a single solution and do not capture the distribution, which is often of interest. We introduce a novel framework that reframes 3D gravity and magnetic joint inversion as a rectified flow on the Noddyverse dataset, the largest physics-based dataset for inversion. We introduce a Ginzburg-Landau (GL) regularizer, a generalized version of the Ising model that aids in ore identification, enabling physics-aware training. We also propose a guidance methodology based on GL theory that can be used as a plug-and-play module with existing unconditional denoisers. Lastly, we also train and release a VAE for the 3D densities, which facilitates downstream work in the field.

cs.LG↗

Does Order Matter : Connecting The Law of Robustness to Robust Generalization

Bubeck and Selke (2021) propose the connection between the Law of Robustness and robust generalization error as an open problem. The Law of Robustness states that overparameterization is necessary for models to interpolate robustly, i.e., the interpolating function is required to be Lipschitz. Wu et al. (2023) extend this law to arbitrary data distributions, proving that the Lipschitz constant satisfies $L = Ω(n^{1/d})$. Robust generalization, on the other hand, asks whether small robust training loss implies small robust test loss. This can be studied using statistical learning techniques such as Rademacher complexities, where a bound on the Rademacher complexity of the robust loss class implies a bound on the Lipschitzness of the function class. We use this connection to explicitly link the two for arbitrary data distributions. (i) We prove that the order of the Lipschitz bound remains the same when considering the global Rademacher complexity of robust loss classes. (ii) At the local scale, i.e., for subsets of functions with small empirical error, the order of the Lipschitz bound changes with the perturbation radius $ρ$ and the localized concentration term $\sqrt{r/n}$.

cs.LG↗