Shlok Singh Sobti

Shlok Singh Sobti

Auto-generated profile, based on publicly available information

Shlok Singh Sobti

Department of Computer Science, Rice University, Houston, TX, USA

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 January 2020 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
Juan HernandezJuan Hernandez
Juan Hernandez
SSShlok Sobti
Shlok Sobti
ASAnthony Sciola
Anthony Sciola
MMMark Moll
Mark Moll
LKLydia Kavraki
Lydia Kavraki
Recently, there has been a growing interest in robotic systems that are able to share workspaces and collaborate with humans. Such collaborative scenarios require efficient mechanisms to communicate human requests to a robot, as well as to transmit robot interpretations and intents to humans. Recent advances in augmented reality (AR) technologies have provided an alternative for such communication. Nonetheless, most of the existing work in human-robot interaction with AR devices is still limited to robot motion programming or teleoperation. In this paper, we present an alternative approach to command and collaborate with robots. Our approach uses an AR interface that allows a user to specify high-level requests to a robot, to preview, approve or modify the computed robot motions. The proposed approach exploits the robot's decision-making capabilities instead of requiring low-level motion specifications provided by the user. The latter is achieved by using a motion planner that can deal with high-level goals corresponding to regions in the robot configuration space. We present a proof of concept to validate our approach in different test scenarios, and we present a discussion of its applicability in collaborative environments.

5 October 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
SSShlok Singh Sobti
Shlok Singh Sobti
The Deflated Sharpe Ratio (DSR) is the standard defence against backtest overfitting. It raises the significance bar with the number of strategies tried, and recent work proposes logging every trial so that DSR can be applied to the true search intensity. We show that counting the backtests actually run is the wrong currency whenever the researcher is adaptive, that is, whenever each new strategy is chosen after seeing earlier validation results. This describes everyday quantitative practice, and it describes LLM research agents and RL alpha miners by construction. First, we prove that a one-line "combine what worked" procedure over k pure-noise strategies drives the validation t-statistic to 2k/π (1+o p (1)), independently of cross-strategy correlation. The DSR bar for the same complete ledger grows only as √ 2 ln k, so DSR certifies noise with probability tending to one. Second, we prove a matching positive result. If the holdout can reveal only a transcript from a set T , then certifying at t > Ḡ-1 (α/|T |) is valid for every adaptive analyst. DSR is the non-adaptive special case |T | = N , and overfitting scales as Θ(√ bits revealed) rather than ln(queries). Under full-precision Sharpe feedback, the only generic valid correction is the classical span (Scheffé/GRS) bound, which grows as √ dim and is unusable at realistic scale. This motivates a sealed holdout: an opaque type whose only operation is a budgeted PASS/FAIL verdict. On synthetic markets, and on 423 real industry strategies (1970-2026) under a stationarybootstrap null, ordinary adaptive workflows such as "rank on validation, keep the top j" are certified by query-counted DSR on 84-100% of pure-noise replicates, and sealed-verdict variants hold false certification at 0.8-3.0%. With frontier code-executing agents (Claude Code), the outcome depends on the instruction. Asked for a robust strategy, the agents usually decline to tune on the holdout. Instructed to maximise validation Sharpe, Claude Opus autonomously executes our attack in about a minute: it sweeps the single signals and then sign-weights the strongest ones, reaching validation t of up to 15.7 on pure noise, against a test t of about 0. Ledger DSR certifies these searches at the attack step under optional stopping (4 of 12 episodes, against 0 of 12 for a non-adaptive baseline) and is rescued only when continued search inflates its variance estimate. A GRPO alpha miner with an AlphaGen-style pool reward learns the same ensemble from reward alone in one of three seeds (177 signals, validation t = 12.0, test t =-0.56), and ledger DSR certifies it. In research campaigns that reuse one holdout across rounds, a researcher who builds on earlier full-precision results makes a false discovery in 100% of 5-round null campaigns, whether certifying by a Bonferroni bar or by cumulative-ledger DSR; splitting the holdout instead cuts power to 0.03 at 10 rounds. The sealed verdict stays at 1-3% while adapting, and keeps power of 0.65-0.79.